Research Engineer - AI Evaluation & Benchmarks (Freelance) at Uber AI Solutions · United States · Joined
US
Research Engineer - AI Evaluation & Benchmarks (Freelance)
Uber AI Solutions · United States · Just now · 0 applicants
NewRemoteContractSenior
Pay
Pay not listed
Workplace
Remote
Job type
Contract
Level
Senior
Source: jobright · Posted by joined-scrapper
About the role
Freelance Research Engineer role designing, implementing, and validating multi-step AI evaluation benchmarks that simulate real-world research engineering workflows, with focus on analyzing model behavior and collaborating with research teams.
What you’ll do
Design, implement, and validate multi-step benchmarks
Build and verify evaluation tasks
Analyze model behavior
Collaborate with research teams
Document benchmarks
What you’ll need
MSc or PhD in a relevant STEM discipline or equivalent practical experience
1+ years of hands-on experience in research engineering, machine learning, data science, or computational AI research
Strong Python programming and scripting skills with modern Git workflows
Solid grounding in machine learning fundamentals and experimental design
Working understanding of LLM capabilities, evaluation frameworks, and common failure patterns
Proficient in statistical analysis, exploratory data handling, and working with complex datasets
Original job description
Uber AI Solutions is seeking a Research Engineer to design, implement, and validate multi-step benchmarks that simulate real-world research engineering workflows. The role involves building and verifying evaluation tasks, analyzing model behavior, collaborating with research teams, and documenting benchmarks.MSc or PhD in Computer Science, Machine…