AI Safety Research Engineer — Production‑Ready & Impactful

AI Chopping Block; San Francisco, Northern (CA, KY); Hybrid; USD 200,000 - 400,000; Full time

Benefits offered by this job

Medical benefits

Life Insurance

Disability benefits

Retirement plan

Parental leave

Wellness stipend

In-office lunches

Flexible vacation

Job summary

Decagon is seeking a Research Engineer focused on Safety to ensure its AI agents are safe, reliable, and controllable in production. You will identify real-world failure modes and build models, evaluations, and safeguards that prevent them.

We expect collaboration with Security, Product, Infrastructure, Legal, and customer teams to translate enterprise requirements into scalable safeguards and rollout practices, shipping high-impact safety improvements.

Qualifications

• 2+ years of experience in AI/ML engineering, research, or AI safety.
• Experience with evaluating, post-training, or deploying language models or agentic systems.
• Experience with adversarial testing, model red teaming, prompt injection, policy enforcement, privacy, or safe tool use.

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/ML engineering

Language models

Adversarial testing

Post-training techniques

Python

Experimentation

Risk assessment

Tools

ML tooling

Job description

Decagon is seeking a Research Engineer focused on Safety to ensure its AI agents are safe, reliable, and controllable in production. You will identify real-world failure modes and build models, evaluations, and safeguards that prevent them.

We expect collaboration with Security, Product, Infrastructure, Legal, and customer teams to translate enterprise requirements into scalable safeguards and rollout practices, shipping high-impact safety improvements.