8 months ago
Redwood City, CA, USAEntry Level / Mid Level / Senior / Staff+
Responsibilities
- Build and operate agent runtime services for tool execution, state management, orchestration, retries, idempotency, and rate limiting.
- Design stable, versioned internal and external APIs, webhook interfaces, and integration adapters.
- Develop schemas and data access patterns for agent memory and state, workflow history, audit trails, permissions, and multi-tenant isolation.
- Implement and maintain OAuth, webhook, synchronization, and connector integrations with observability and failure handling.
- Improve reliability through SLIs/SLOs, end-to-end tracing, timeouts, circuit breakers, budgets, and incident response.
- Optimize throughput, latency, queues, caching, storage, inference costs, and tool-call costs while adding safeguards for runaway tasks.
- Raise engineering standards through testing strategy, on-call practices, runbooks, postmortems, code quality, and mentoring.
Requirements
- 6+ years of experience building backend systems for production SaaS, platforms, or distributed systems.
- Strong backend fundamentals in distributed systems, concurrency, queues and workers, caching, and production operations.
- Expertise in relational data modeling with Postgres or MySQL, including migrations, indexing, query optimization, and data correctness.
- Proven ability to design clear, evolvable APIs and service contracts for internal services and external partners.
- Ability to work quickly while maintaining reliability and security, take ownership of systems end-to-end, and operate effectively amid ambiguity.
- Preferred experience building products with LLMs, including prompting, tool calling, evaluations, and latency/cost tradeoffs.
- Preferred familiarity with agent orchestration, planning and execution loops, memory and state, sandboxed tool execution, human-in-the-loop workflows, and safety constraints.
- Preferred familiarity with Vercel AI SDK, LangChain/LangGraph, Anthropic Agents SDK, OpenAI tool calling, and sandboxing or tool runtimes.
Benefits
- Medical, dental, and vision coverage beginning on day one.
- Unlimited PTO with a requirement to take at least one continuous week off each year.
- 401(k) with company match.
- Remote-flexible work arrangement with office attendance when needed.
- Parental leave benefits.
- Ongoing industry and professional development training.
- Employee-led culture committee.
Tech Stack
MySQLPostgreSQL
Categories
