Research Engineer, Safety

The role

You will research and build safeguards to make AI agents safe, reliable, and controllable. You will develop evaluations, classifiers, and post-training methods to prevent failure modes like prompt injection and hallucinations.

What you will do

• Research and build safeguards against prompt injection, unsafe tool use, sensitive-data disclosure, policy violations, and hallucinated commitments
• Build adversarial evaluations, simulations, red-team datasets, and regression suites
• Develop and deploy classifiers, judges, reward signals, post-training methods, and runtime safeguards
• Analyze production traces and incidents to identify root causes and test mitigations
• Partner with Security, Product, Infrastructure, Legal, and customer-facing teams

Required qualifications

• 2+ years of experience in AI/ML engineering, research, or AI safety
• 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
• Strong experimental judgment and the engineering depth to ship production systems
• Comfort owning ambiguous, high-stakes technical problems and making clear risk and product tradeoffs

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

Benefits

• Medical, Dental, and Vision benefits for you and your family
• Life Insurance and Disability Benefits
• Retirement Plan (e.g., 401K, pension)
• Parental Leave
• Fertility and family building benefits through Carrot
• Monthly stipend to support your wellness, lifestyle, and work-life balance
• Daily lunches and snacks in the office
• Take what you need vacation policy

About the company

Decagon is a conversational AI platform that enables enterprises to deploy AI agents across various channels. The company is an in-office company driven by values like Just Get It Done and The Polymath Principle.