Research Engineer, Safety
Decagon · San Francisco · New York City
Applied AIonsite$200k–$400k
At a glance
Highlights
- Build safeguards against prompt injection, unsafe tool use and data disclosure.
- Develop adversarial evaluations, simulations and red-team datasets from failures.
- Ship models and runtime safeguards for safer enterprise conversational agents.
What they offer
- Competitive equity
- Medical, dental and vision benefits for you and family
- 401K retirement plan
- Parental leave and fertility benefits through Carrot
- Monthly wellness stipend and daily lunches
Ideal candidate
Applied AI safety-minded engineer who loves owning ambiguous, high-stakes problems end-to-end and shipping reliable safeguards that make enterprise agents safe in production.
Requirements
- 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 including RL, preference optimization and synthetic-data generation
- Experience with adversarial testing, red teaming, prompt injection, policy enforcement, privacy or safe tool use
- Fluency in Python and modern ML tooling with engineering depth to ship production systems
- Comfort owning ambiguous, high-stakes technical problems and making risk tradeoffs
- remote policy
- in-office
Lab profile
About Decagon
Leading conversational AI platform empowering brands with concierge customer experiences via AI agents.
What they build
- Conversational AI platform
- AI agents for voice, chat, email and SMS
Known for
- Concierge customer experiences
- Personalized interactions across every channel
- Trusted by enterprises like Avis, Block, Chime and Oura
Posted · Last seen