Uber AI Solutions
Research Engineer – Generative AI & LLM Evaluation
Share this job
Job Description
Research Engineer – Generative AI & LLM Evaluation
Freelance / Independent Contractor (1099) | 100% Remote
About Uber AI Solutions
Uber AI Solutions connects experienced industry professionals and researchers with leading Generative AI labs and enterprise product teams to advance the capabilities of next-generation AI models.
About the Opportunity
We are seeking experienced Research Engineers for a freelance engagement focused on designing, developing, and validating complex technical benchmarks for advanced AI models.
The project involves creating realistic engineering challenges that evaluate how AI models plan, write code, debug, conduct experiments, and solve multi-step technical problems.
Key Responsibilities
- Design and develop complex benchmark tasks for evaluating AI models.
- Create technical challenges involving Python programming, debugging, experimentation, and quantitative reasoning.
- Evaluate LLM outputs and identify model limitations, failure patterns, and edge cases.
- Validate tasks for technical accuracy, reproducibility, and difficulty.
- Collaborate with research teams to improve evaluation methodologies.
- Prepare technical documentation, reference solutions, and evaluation rubrics.
Required Qualifications
- MSc or PhD in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Mathematics, Physics, or a related STEM discipline. Equivalent practical research experience will also be considered.
- At least 1 year of relevant experience in Research Engineering, Machine Learning, Data Science, or computational AI research.
- Strong proficiency in Python programming, scripting, Git, and debugging.
- Understanding of machine learning fundamentals, LLM capabilities, and evaluation methodologies.
- Experience with statistical analysis, Jupyter Notebooks, Google Colab, and experimental workflows.
- Strong analytical, problem-solving, and technical documentation skills.
Preferred Qualifications
- Experience developing AI/ML evaluation benchmarks.
- Familiarity with agentic AI workflows, prompt engineering, AI safety, or Reinforcement Learning.
- Experience using AI coding tools such as Cursor, GitHub Copilot, Gemini, or JetBrains AI.
Engagement Details
- Engagement Type: Freelance / Independent Contractor (1099)
- Work Arrangement: 100% Remote
- Location: Remote
Please Note
This is an independent contractor engagement, not a permanent full-time employment position.
Pay: $100.00 - $130.00 per hour
Expected hours: 35.0 per week
Work Location: Remote
Keep looking