Senior Research Engineer, Safety
Core
Research and build safeguards against prompt injection, unsafe tool use, sensitive-data disclosure, policy violations, and hallucinated commitments for AI agents.
Role type
Senior Research Engineer (AI Safety)
Builds
Adversarial evaluations, simulations, red-team datasets, regression suites, classifiers, judges, reward signals, and runtime safeguards.
Domain
AI Safety / LLM Security / Agentic Systems
Deliverable
production ML models
Required skills
AI/ML engineering, language model evaluation, post-training, reinforcement learning, preference optimization, distillation, model routing, synthetic-data generation, adversarial testing, model red teaming, prompt injection defense, policy enforcement, privacy engineering, Python, production system deployment
Preferred skills
high-stakes enterprise workflow safeguards, human-in-the-loop review, incident response, responsible ML rollout frameworks
Technologies
Python, modern ML tooling
Responsibilities
Build adversarial evaluations and red-team datasets; Develop and deploy classifiers and runtime safeguards; Analyze production traces to identify root causes and test mitigations; Partner with cross-functional teams to turn enterprise requirements into scalable safeguards
Seniority
Senior, hands-on IC