Decagon
Research Engineer, Safety
$200K–$400K
San Francisco +1 · Full-time · Posted Sep 4, 2026
- Location
- San Francisco
New York City - Experience
- 2+ years in AI/ML engineering, research, or AI safety.
About the job
Build and deploy safety models, evaluations, and safeguards that make Decagon’s conversational AI agents reliable and controllable from testing through production.
What you'll do
- Research and build safeguards against prompt injection, unsafe tool use, sensitive-data disclosure, policy violations, and hallucinated commitments.
- Develop adversarial evaluations, simulations, red-team datasets, and regression suites informed by production failures.
- Analyze production incidents and traces, deploy mitigations, and partner across teams to scale safety practices.
What they ask for
- Hands-on experience evaluating, post-training, or deploying language models or agentic systems.
- Experience with modern post-training techniques, such as reinforcement learning, preference optimization, distillation, model routing, and synthetic-data generation.
- Experience with adversarial testing, model red teaming, prompt injection, policy enforcement, privacy, or safe tool use.
- Fluency in Python and modern ML tooling, with strong experimental judgment and production engineering depth.
Nice to have
- Experience building safeguards for high-stakes or regulated enterprise workflows.
- Familiarity with human-in-the-loop review, incident response, or responsible rollout frameworks for ML systems.
Pay
$200K – $400K USD base salary
Tools
Python
AI focus
Applied AI safety for conversational agents, including evaluation, post-training, safeguards, and runtime controls.
Model-written summary · the original posting is authoritative