Senior Research Engineer, Safety

Written by the T&S Network from Decagon's posting.

Safety research engineering for Decagon's enterprise conversational AI agents, covering evaluation through production. The Research team builds the model and decision-making stack behind customer support agents, and this role sits in its safety work, focused on finding real-world failure modes and building the models, evaluations and safeguards that prevent them.

• AI misuse and jailbreaks

What you'd do

• Create guardrails that block prompt injection, misuse of tools, leaking sensitive data, rule-breaking and invented promises to customers.
• Construct stress tests, simulated conversations, red-team datasets and regression checks drawn from failures seen in production.
• Work with Security, Product, Infrastructure, Legal and customer-facing staff to convert enterprise demands into safeguards that scale and rollout procedures.
• Analyze live conversation logs and incidents to trace causes, try fixes and gauge how much each one helps.

What it asks for

• Hands-on experience evaluating, post-training or deploying language models or agentic systems.
• Fluency in Python and modern ML tooling, with engineering depth to ship production systems.
• Familiarity with human review loops, incident response or responsible rollout frameworks for ML systems (preferred).

Terms in this role

Red teaming.

Testing a system, often an AI model, by deliberately trying to make it fail or misbehave, so problems are found and fixed first.

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Decagonnorth_east before you apply. If we got something wrong, report this listing.