Decagon
Senior Software Engineer, Agent Platform
$200K–$400K
San Francisco · On-site · Senior · Full-time · Posted Nov 19, 2025
About the job
Build and operate the agent runtime, orchestration, and experimentation systems that help Decagon’s AI agents perform reliably in production.
What you'll do
- Design and evolve agent harnesses, runtime systems, and multi-model orchestration.
- Build routing, planning, and tool-invocation control-plane logic; improve latency, reliability, safety, and observability.
- Analyze production failures and run online experiments and offline evaluations to improve agent behavior.
What they ask for
- Strong experience building distributed systems or backend platforms in production.
- Experience owning systems end-to-end, from design through production and iteration.
- Familiarity with experimentation, evaluation, or data-driven product improvement.
- Track record improving reliability, performance, and observability; ability to debug complex systems.
Nice to have
- Experience with agent harnesses, orchestration layers, or execution frameworks.
- Interest in control planes, feedback loops, system-level optimization, and improving intelligent systems.
Pay
$200K – $400K (base salary); equity offered, amount not stated
AI focus
Develop agent harnesses and orchestration systems that coordinate models, workflows, and tools; improve agent reasoning, execution reliability, safety, and performance through evaluation and experimentation.
Model-written summary · the original posting is authoritative