AI Safety Research Engineer — Production Safeguards & Equity

Decagon; New York (NY); On-site; USD 200,000 - 400,000; Full time

Benefits offered by this job

Medical, Dental, and Vision benefits

401K retirement plan

Parental Leave

Equity opportunities

Daily lunches in the office

Job summary

Decagon is leading the conversational AI platform enabling brands to deploy agents across voice, chat, and email channels. We seek a Research Engineer focused on Safety to make our agents safe, reliable, and controllable from evaluation through production.

You’ll own end-to-end work, ship real improvements, and collaborate with Security, Product, and Legal to implement scalable safeguards that prevent real-world failures.

Qualifications

• 2+ years of experience in AI/ML engineering, research, or AI safety.
• Hands-on experience evaluating, post-training, or deploying language models.
• Experience with post-training techniques such as reinforcement learning, preference optimization, distillation.
• 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.
• Comfort owning ambiguous, high-stakes technical problems and making risk tradeoffs.

Responsibilities

• 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 informed by production failures.
• Develop and deploy classifiers, judges, reward signals, post-training methods, and runtime safeguards for safer agent behavior.
• Analyze production traces and incidents to identify root causes, test mitigations, and measure their impact.
• Partner with Security, Product, Infrastructure, Legal, and customer-facing teams to turn enterprise requirements into scalable safeguards and rollout practices.

Skills

AI safety

ML engineering

Safety evaluation

Job description

Decagon is leading the conversational AI platform enabling brands to deploy agents across voice, chat, and email channels. We seek a Research Engineer focused on Safety to make our agents safe, reliable, and controllable from evaluation through production.

You’ll own end-to-end work, ship real improvements, and collaborate with Security, Product, and Legal to implement scalable safeguards that prevent real-world failures.