1d ago
Research Engineer, Agents
San Francisco
$200k-$400k / year
full-timesoftware
๐ผ About This Role
You'll design and build the orchestration systems that power Decagon's AI agents in production, owning the runtime and control-plane logic for routing, planning, and tool invocation. Your work will directly impact agent reliability across millions of interactions, as you quickly iterate to improve quality and capability in a fast-moving, experimental environment.
๐ฏ What You'll Do
- Design and evolve agent harnesses for different product experiences
- Build core runtime systems including AOP execution and multi-model orchestration
- Develop control-plane logic for routing, planning, and tool invocation
- Analyze real-world failures to drive iterative improvements
๐ Requirements
- Strong experience building distributed systems or backend platforms in production
- Comfort working in ambiguous, fast-moving environments with rapid iteration cycles
- Experience owning systems end-to-end from design through production and iteration
- Ability to debug complex systems and identify root causes of failures
โจ Nice to Have
- Built or worked on agent harnesses, orchestration layers, or execution frameworks
- Experience with experimentation, evaluation, or data-driven product improvement loops
๐ Benefits & Perks
- ๐๏ธ Take what you need vacation policy (subject to local requirements)
- ๐ฉบ Medical, Dental, and Vision benefits for you and your family
- ๐ฐ Equity as part of compensation
- ๐ถ Parental Leave and fertility benefits through Carrot
- ๐ฝ๏ธ Daily lunches provided in-office
๐จ Hiring Process
Estimated timeline: 2-4 weeks ยท AI estimate
- 1Recruiter callยท 30 min
- 2Technical interviewยท 60 min
- 3Onsite interviewsยท half day
0 0 0