Braintrust is the agent observability platform. By actively applying intelligence to agent traces and automatically surfacing the most critical patterns, Braintrust gives teams the visibility to understand how agents behave in production and the tools to improve them.
Teams at Notion, Stripe, Box, OpenAI, and Cloudflare use Braintrust to trace their agents, find the issues in their observability data, and run evals that tell them how to improve.
We’re looking for a Detection and Response engineer to design and build systems that identify, analyze, and eradicate threats across the Braintrust stack. You’ll practice detection-as-code, run security operations with agents, lead incident response, and stay ahead of the curve incorporating real-time threat intelligence. Have a big impact with a small team that has outsized capabilities.
What you'll doBuild security telemetry pipelines across cloud execution environments (ECS/K8s), CI/CD systems, identity systems, endpoints, and agentic workloads
Continuously improve detections for attacks, abuse, and anomalous behavior
Own the alert pipeline end-to-end and keep signal-to-noise high
Lead incident response and participate in on-call: triage, scope, contain, and remediate incidents, then write postmortems that produce durable improvements
Hunt proactively for threats and build the tooling for turning evidence into new detections
Build agents that triage alerts, enrich findings, gather evidence, and scope incidents, with human-in-the-loop controls and evals that keep the automation trustworthy
Run vulnerability response, evaluating impact and driving remediation across our infrastructure
Proficient in modern backend technologies and comfortable writing real code in Python, TypeScript, or Go
AWS experience (IAM, VPC, KMS, GuardDuty, CloudTrail) and working fluency in at least one of Azure or GCP
Kubernetes detection experience: audit logs, runtime telemetry, and workload identity
Knowledge of endpoint security (MacOS) and detection and response techniques
Hands-on incident experience: you’ve been on call, led incidents, and written postmortems
Strong written and verbal communication
A clear point of view on AI/LLM security and hands-on experience defending relevant threats
Bonus: prior experience with LLM red-teaming, agent sandbox research, or other AI-relevant security threat defense
Medical, dental, and vision insurance
Daily lunch, snacks, and beverages
Flexible time off
Competitive salary and equity
Wifi & cellphone stipend
Braintrust is an equal opportunity employer. All applicants will be considered for employment without attention to race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status.
Skills Required
- Proficiency in modern backend technologies and ability to write production code in Python, TypeScript, or Go
- AWS experience with IAM, VPC, KMS, GuardDuty, and CloudTrail
- Working fluency in at least one of Azure or GCP
- Kubernetes detection experience, including audit logs, runtime telemetry, and workload identity
- Knowledge of macOS endpoint security and detection and response techniques
- Hands-on incident response experience, including on-call participation, incident leadership, and postmortem writing
- Strong written and verbal communication skills
- Clear perspective on AI/LLM security and hands-on experience defending relevant threats
- Experience with LLM red-teaming, agent sandbox research, or other AI-relevant security threat defense
What We Do
Braintrust is an AI-native observability platform that helps teams measure, evaluate, and improve AI models and products in production.
