4 hours ago
Responsibilities
- Design agent architectures for planning, reasoning, tool use, memory, and integrations with external systems and data.
- Improve reliability and failure recovery for long-running, multi-step tasks.
- Build feedback loops that enable agents to improve through real-world use.
- Develop rigorous, game-resistant evaluations of agent performance.
- Build execution tracing and observability systems with a focus on reproducibility.
- Balance quality, latency, cost, and system complexity.
Requirements
- 5+ years of experience building production ML or backend systems.
- Experience taking LLM or agent applications from prototype to production.
- Strong understanding of agent planning, reasoning, tool use, orchestration, and memory.
- Experience building rigorous evaluation systems, execution tracing, and observability for agents.
- Familiarity with the OpenAI Responses API, MCP, and server-side versus client-side execution.
- Adaptability, strong collaboration, and willingness to develop bold ideas.
Benefits
- Flexible work options including in-person collaboration in the Bay Area, distributed global-first work, and team offsites.
- Annual Adaption Passport travel stipend to explore a country never previously visited.
- Weekly lunch stipend for take-out or grocery delivery.
- Comprehensive medical benefits and generous paid time off.
Categories
About adaption
Adaption builds AI systems that adapt as real world conditions change. Moving beyond static and costly retraining cycles, Adaption delivers intelligence that evolves through real world interaction, enabling efficient AI across domains, languages and operational constraints.