Senior AI Safety Research Engineer

Speedrun Talent Network; San Francisco, Northern (CA, KY); Hybrid; USD 200,000 - 400,000; Full time

Benefits offered by this job

Medical, Dental, and Vision benefits

Life Insurance and Disability Benefits

Retirement Plan (e.g., 401K)

Parental Leave

Fertility and family building benefits

Monthly wellness stipend

Daily lunches and snacks in the office

Take what you need vacation policy

Job summary

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

We hire strong engineers who own their work end-to-end, ship real improvements, and make high-impact technical decisions in a fast-paced, in-office environment.

Qualifications

• 4+ years of experience in AI/ML engineering or AI safety.
• Experience evaluating, post-training, or deploying language models or agentic systems.
• Experience with post-training techniques, such as reinforcement learning.
• 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 the engineering depth to ship production systems.
• Comfort owning ambiguous, high-stakes technical problems and making clear risk and product tradeoffs.

Responsibilities

• Research safeguards against prompt injection, unsafe tool use, data exposure, policy violations, and hallucinations.
• Build adversarial evaluations, simulations, red-team datasets, and regression suites from production failures.
• Develop classifiers and runtime safeguards for safer agent behavior.
• Analyze production traces to identify root causes and test mitigations.
• Collaborate with Security, Product, Infrastructure, Legal to scale safeguards and rollout practices.

Skills

AI/ML engineering

Python

post-training techniques

adversarial testing

production systems

Job description

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

We hire strong engineers who own their work end-to-end, ship real improvements, and make high-impact technical decisions in a fast-paced, in-office environment.