4 months ago
Remote, United StatesSenior
Responsibilities
- Design and develop coding benchmarks for evaluating frontier AI models.
- Analyze AI-generated code for correctness, reliability, efficiency, and edge cases.
- Build and maintain scalable data pipelines supporting AI evaluation workflows.
- Create structured programming scenarios that test reasoning, debugging, and code quality.
- Work with large codebases and multi-language software environments.
- Write clean, maintainable, and well-tested Python code.
- Collaborate with teams improving how AI models understand, generate, and evaluate software.
Requirements
- At least 4 years of professional software engineering experience.
- Expert-level proficiency in Python.
- Experience at a high-growth technology company or top-tier software organization.
- Proficiency in at least one additional language such as JavaScript, Go, or C++.
- Experience with CI/CD pipelines and automated testing frameworks such as pytest, Mocha, or JUnit.
- Strong understanding of software engineering best practices, debugging, and code quality.
- Strong analytical and problem-solving skills.
- Preferred: experience with AI/ML evaluation, model benchmarking, or generative AI.
- Preferred: background in security engineering.
- Preferred: significant open-source software contributions.
- Preferred: experience with large-scale distributed systems or enterprise software platforms.
Benefits
- Fully remote contract opportunity.
- Expected workload is 10–39 hours per week, depending on project needs.
- Weekly payments are provided for approved work completed during the previous week.
- Work volume may fluctuate throughout the engagement.
- Candidates submit a proposal, complete a qualification form, receive an Upwork contract offer if qualified, and proceed through an evaluation and technical interview.
Tech Stack
Categories
About Lifted
Lifted builds a global platform for enterprises to source, contract, manage, and pay contingent workers with embedded compliance. The software integrates into existing contingent workforce ecosystems and supports multiple worker types across countries. Lifted operates as an Upwork company, serving organizations that need to centralize contingent programs and streamline cross‑border payments and documentation.