Skills Profile
Develops evals, benchmarks and quality metrics for LLM systems. Core responsibilities include Python, Experiment Design & Causal Inference and Statistics & Data Analysis. Day-to-day work involves tools such as Large Language Model Integration (LLM, OpenAI/LangChain) and AI Coding Assistants (Copilot/Claude). The position also requires solid skills in Natural Language Processing and Debugging & Code-Level Root Cause Analysis.Develops evals, benchmarks and quality metrics for LLM systems. Core responsibilities include Python, Experiment Design & Causal Inference and Statistics & Data Analysis. Day-to-day work involves tools such as Large Language Model Integration (LLM, OpenAI/LangChain) and AI Coding Assistants (Copilot/Claude). The position also requires solid skills in Natural Language Processing and Debugging & Code-Level Root Cause Analysis.Develops evals, benchmarks and quality metrics for LLM systems. Core responsibilities include Python, Experiment Design & Causal Inference and Statistics & Data Analysis. Day-to-day work involves tools such as Large Language Model Integration (LLM, OpenAI/LangChain) and AI Coding Assistants (Copilot/Claude). The position also requires solid skills in Natural Language Processing and Debugging & Code-Level Root Cause Analysis.
Your match
How close are you to LLM Evaluation Engineer?
Develop applications, scripts and data analyses with Python. Covers implementing new features, reading and refactoring existing code, writing tests, and working with package managers, debugging tools and the ecosystem's tooling.Develop applications, scripts and data analyses with Python. Covers implementing new features, reading and refactoring existing code, writing tests, and working with package managers, debugging tools and the ecosystem's tooling.Develop applications, scripts and data analyses with Python. Covers implementing new features, reading and refactoring existing code, writing tests, and working with package managers, debugging tools and the ecosystem's tooling.
Develop applications, scripts and data analyses with Python. Covers implementing new features, reading and refactoring existing code, writing tests, and working with package managers, debugging tools and the ecosystem's tooling.Develop applications, scripts and data analyses with Python. Covers implementing new features, reading and refactoring existing code, writing tests, and working with package managers, debugging tools and the ecosystem's tooling.Develop applications, scripts and data analyses with Python. Covers implementing new features, reading and refactoring existing code, writing tests, and working with package managers, debugging tools and the ecosystem's tooling.
Isolate, debug and durably fix defects. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Isolate, debug and durably fix defects. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Isolate, debug and durably fix defects. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.
Isolate, debug and durably fix defects. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Isolate, debug and durably fix defects. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Isolate, debug and durably fix defects. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.
Design and evaluate experiments with statistical rigour. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Design and evaluate experiments with statistical rigour. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Design and evaluate experiments with statistical rigour. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.
Design and evaluate experiments with statistical rigour. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Design and evaluate experiments with statistical rigour. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Design and evaluate experiments with statistical rigour. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.
Build LLM applications with APIs, agents and tool use. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Build LLM applications with APIs, agents and tool use. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Build LLM applications with APIs, agents and tool use. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Build LLM applications with APIs, agents and tool use. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Build LLM applications with APIs, agents and tool use. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Build LLM applications with APIs, agents and tool use. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Process language data and build LLM applications. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Process language data and build LLM applications. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Process language data and build LLM applications. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Process language data and build LLM applications. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Process language data and build LLM applications. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Process language data and build LLM applications. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Analyse and interpret data using statistical methods. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Analyse and interpret data using statistical methods. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Analyse and interpret data using statistical methods. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.
Analyse and interpret data using statistical methods. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Analyse and interpret data using statistical methods. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.Analyse and interpret data using statistical methods. Covers preparing and quality-assuring the data, methodologically sound analysis, visualising results and presenting them audience-appropriately as a basis for decisions.
Integrate AI assistants productively into development work. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Integrate AI assistants productively into development work. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Integrate AI assistants productively into development work. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Integrate AI assistants productively into development work. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Integrate AI assistants productively into development work. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Integrate AI assistants productively into development work. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Use generative AI tools productively and responsibly. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Use generative AI tools productively and responsibly. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Use generative AI tools productively and responsibly. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Use generative AI tools productively and responsibly. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Use generative AI tools productively and responsibly. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Use generative AI tools productively and responsibly. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Manage source code with Git and merge work in teams. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage source code with Git and merge work in teams. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage source code with Git and merge work in teams. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Manage source code with Git and merge work in teams. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage source code with Git and merge work in teams. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage source code with Git and merge work in teams. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Apply measuring equipment and document test results. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Apply measuring equipment and document test results. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Apply measuring equipment and document test results. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Apply measuring equipment and document test results. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Apply measuring equipment and document test results. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Apply measuring equipment and document test results. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Analyse data with formulas, pivot tables and charts. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Analyse data with formulas, pivot tables and charts. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Analyse data with formulas, pivot tables and charts. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Analyse data with formulas, pivot tables and charts. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Analyse data with formulas, pivot tables and charts. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Analyse data with formulas, pivot tables and charts. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Manage documents, emails and appointments with Microsoft Office. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage documents, emails and appointments with Microsoft Office. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage documents, emails and appointments with Microsoft Office. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Manage documents, emails and appointments with Microsoft Office. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage documents, emails and appointments with Microsoft Office. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Manage documents, emails and appointments with Microsoft Office. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Describe requirements in structured specification documents and align them with stakeholders.Describe requirements in structured specification documents and align them with stakeholders.Describe requirements in structured specification documents and align them with stakeholders.
Describe requirements in structured specification documents and align them with stakeholders.Describe requirements in structured specification documents and align them with stakeholders.Describe requirements in structured specification documents and align them with stakeholders.
Know relevant standards and apply them in projects. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Know relevant standards and apply them in projects. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Know relevant standards and apply them in projects. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Know relevant standards and apply them in projects. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Know relevant standards and apply them in projects. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Know relevant standards and apply them in projects. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Create manuals and specifications to standards. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create manuals and specifications to standards. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create manuals and specifications to standards. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Create manuals and specifications to standards. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create manuals and specifications to standards. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create manuals and specifications to standards. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Estimate effort (story points, planning poker) and plan sprints realistically.Estimate effort (story points, planning poker) and plan sprints realistically.Estimate effort (story points, planning poker) and plan sprints realistically.
Estimate effort (story points, planning poker) and plan sprints realistically.Estimate effort (story points, planning poker) and plan sprints realistically.Estimate effort (story points, planning poker) and plan sprints realistically.
Organise backlogs, boards and docs in Jira and Confluence. Covers confident day-to-day use: data maintenance and quality, configuration of processes and workflows, analyses and reports, and onboarding of new users.Organise backlogs, boards and docs in Jira and Confluence. Covers confident day-to-day use: data maintenance and quality, configuration of processes and workflows, analyses and reports, and onboarding of new users.Organise backlogs, boards and docs in Jira and Confluence. Covers confident day-to-day use: data maintenance and quality, configuration of processes and workflows, analyses and reports, and onboarding of new users.
Organise backlogs, boards and docs in Jira and Confluence. Covers confident day-to-day use: data maintenance and quality, configuration of processes and workflows, analyses and reports, and onboarding of new users.Organise backlogs, boards and docs in Jira and Confluence. Covers confident day-to-day use: data maintenance and quality, configuration of processes and workflows, analyses and reports, and onboarding of new users.Organise backlogs, boards and docs in Jira and Confluence. Covers confident day-to-day use: data maintenance and quality, configuration of processes and workflows, analyses and reports, and onboarding of new users.
Create models, simulations and analyses in MATLAB/Simulink. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create models, simulations and analyses in MATLAB/Simulink. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create models, simulations and analyses in MATLAB/Simulink. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
Create models, simulations and analyses in MATLAB/Simulink. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create models, simulations and analyses in MATLAB/Simulink. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.Create models, simulations and analyses in MATLAB/Simulink. In practice this covers independent execution, quality assurance of one's own results, and close alignment with adjacent roles and interfaces.
See where you stand for LLM Evaluation Engineer.
Assess 18 skills, see your match and gaps. Free.