Remote Senior Python Engineer: AI Benchmarking & Evaluation

Lifted (Upwork); United States; Remote; USD 110,000 - 138,000; Part time

Benefits offered by this job

Fully remote contract

Job summary

Lifted is seeking a senior software engineer with expert Python skills to help design benchmarks, evaluate AI-generated code, and build scalable data pipelines for AI evaluation.

You will work on large codebases, test reasoning and debugging, and collaborate with teams to improve how models understand, generate, and assess software, while delivering clean, well-tested Python.

This is a fully remote contract with an hourly rate and flexible workload up to 39 hours per week.

Qualifications

• 4+ years of professional software engineering experience.
• Expert-level proficiency in Python.
• Experience with CI/CD pipelines and automated testing frameworks such as pytest, Mocha, or JUnit.
• Proficiency in at least one additional programming language (JavaScript, Go or C++).

Responsibilities

• Design and develop coding benchmarks used to evaluate frontier AI models.
• Analyze AI-generated code for correctness, reliability, efficiency, and edge cases; build scalable data pipelines for AI evaluation workflows.
• Create structured programming scenarios to test reasoning, debugging, and code quality.
• Work with large codebases and multi-language software environments.
• Collaborate with teams to improve how AI models understand, generate, and evaluate software.
• Write clean, maintainable, and well-tested Python code following software engineering best practices.

Skills

Python

4+ years experience

Additional language (JS/Go/C++)

CI/CD pipelines

Testing frameworks (pytest/Mocha/JUnit

Code quality & debugging

Tools

pytest

Mocha

JUnit

Job description

Lifted is seeking a senior software engineer with expert Python skills to help design benchmarks, evaluate AI-generated code, and build scalable data pipelines for AI evaluation.

You will work on large codebases, test reasoning and debugging, and collaborate with teams to improve how models understand, generate, and assess software, while delivering clean, well-tested Python.

This is a fully remote contract with an hourly rate and flexible workload up to 39 hours per week.