SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
You will build the agent systems at the core of Adaption's product, turning customer goals into reliable, multi-step execution across real tools and services. This role focuses on production-grade agent systems operating under real constraints: incomplete information, external failures, limited budgets, and unpredictable traffic.
Key responsibilities include:
- Design agent architectures for planning, reasoning, tool use, memory, and integration with external systems and data.
- Improve reliability on long-running, multi-step tasks, including failure recovery and error handling.
- Build feedback loops that enable agents to improve with real-world use, so performance compounds over time rather than remaining static.
- Develop rigorous evaluation systems that measure agent performance and resist gaming.
- Make practical tradeoffs between quality, latency, cost, and complexity.
You'll own how agents plan, use tools, recover from errors, and improve iteratively. This is not about building demos—you'll work on production systems that handle real-world complexity and scale.
Adaption is building efficient intelligence that evolves in real-time. The company's vision centers on AI systems that are flexible, personalized, and accessible. The team emphasizes talent density and is looking for builders and creative thinkers ready to shape the next era of intelligence.
The role offers hybrid work with in-person collaboration in the Bay Area, a distributed global-first team structure, and team offsites. Benefits include an annual travel stipend (Adaption Passport), weekly meal allowance, comprehensive medical benefits, and generous paid time off.
QUALIFICATIONS:
- 5+ years building production ML or backend systems, including taking LLM or agent applications from prototype to production.
- Strong understanding of agent design: planning, reasoning, tool use, orchestration, and memory.
- Experience building rigorous evaluation systems, plus execution tracing and observability for agents, with a focus on reproducibility.
- Familiarity with the OpenAI Responses API, MCP, and server- versus client-side execution tradeoffs.
- Adaptability and collaborative mindset; willingness to take bold ideas to production.
