← Toutes les offres
Snorkel AI

Research Scientist (Open Benchmarks Red Team)

Snorkel AI

New York
CDI
Intelligence artificielle / Machine Learning
Publié le 22 novembre 2026

Description du poste

Familiarity with LLM/agent benchmarks, evaluation frameworks, or automated grading systems Strong research or engineering background in machine learning, LLMs, AI agents, and evaluation Experience independently driving research and engineering projects from problem identification through implementation and validation Experience designing rigorous experiments, analyzing model behavior, and investigating unexpected failures Ability to identify weaknesses in existing evaluation methods, develop new approaches, and rigorously test whether they work Strong communication and collaboration skills Strong Python programming skills and experience building, running, and debugging AI agents or evaluation systems Experience with adversarial testing, red teaming, reward hacking, or specification gaming Experience developing or evaluating benchmarks for coding agents, computer use, professional workflows, etc Familiarity with RL environments, agent trajectories, verifiers, and evaluation infrastructure Open-source contributions or publications in AI evaluation, robustness, or agentic systems PhD in Computer Science, Machine Learning, or a related field, or equivalent research/industry experience Snorkel AI is hiring researchers to support the Open Benchmarks Red Team program Frontier AI benchmarks can contain grading failures, exploitable shortcuts, and task errors that make results unreliable. We’re looking for a Research Scientist / Research Engineer to identify benchmark weaknesses, help develop and validate fixes, and create reusable methods to improve benchmark quality across tasks and datasets This is a hands-on research role combining AI evaluation, adversarial testing, practical benchmark repairs, and close collaboration with benchmark authors. You’ll share findings with benchmark authors, work together on fixes, and help get improved benchmark versions adopted Red-team frontier benchmarks: Identify and reproduce issues such as reward hacking, grader failures, task ambiguity, shortcuts, and environment vulnerabilities Develop benchmark repairs: Propose next steps for validated issues, implement selected fixes with benchmark authors, and verify fixes without breaking valid solutions Develop reusable methods: Reuse existing tools where possible and develop new checks to detect recurring benchmark weaknesses Collaborate with benchmark authors: Review findings with benchmark authors before publication, collaborate on repairs, and support official improved releases Drive research impact: Contribute to technical reports, open-source tools, publications, and new approaches to benchmark evaluation and improvement Benefits Health: Snorkelers and their dependents are covered by comprehensive medical, dental, and vision plans. Wellness: All Snorkelers get a yearly wellness stipend to use on anything related to health and well-being. PTO and rest days: We provide unlimited personal time off so you can find your work-life balance. Plus, two company-wide rest days per quarter in addition to company holidays. One global team: From our headquarters in Redwood City, CA, to regional offices in San Francisco and New York, we work together as one global team. Events: Get to know your fellow Snorkelers outside of work! We host regular events and learning opportunities for our teams across our offices and virtually to connect, have fun, and grow. Family leave: Snorkel offers generous parental leave for both birthing and non-birthing parents based on eligibility.