Senior Backend Engineer — AI Agents Platform

About the role

We’re building a large-scale, highly reliable platform for vertical AI agents. Our agents execute real workflows: they call tools, integrate with third-party systems, and operate over complex, evolving data. This role owns the backend systems that make agents dependable in production—agent runtime services, integrations, data modeling, observability, and platform reliability.

What You’ll Do

• Own core backend services powering agents: build and operate the agent runtime services (tool execution, state management, orchestration, retries, idempotency, rate limiting).
• Design robust APIs and contracts: develop stable, well-versioned APIs (internal + external), including webhook/event interfaces and integration adapters.
• Model complex domain data: design schemas and data access patterns that support agent memory/state, workflow history, audit trails, permissions, and multi-tenant isolation.
• Implement and maintain high-quality integrations (OAuth, webhooks, sync engines, connectors) with strong observability and failure handling.
• Define and improve SLIs/SLOs, implement end-to-end tracing, build safety rails (timeouts, circuit breakers, budgets), and run incident response.
• Optimize platform performance and cost control: optimize throughput/latency, queue backlogs, caching, storage, and inference/tool-call costs; build guardrails for runaway tasks.
• Raise engineering standards: drive code quality, testing strategy, on-call hygiene, runbooks, postmortems, and mentoring.

What We’re Looking For

• Experience: 6+ years building backend systems for production SaaS, platforms, or distributed systems.
• Backend depth: strong fundamentals in distributed systems, concurrency, queues/workers, caching, and production operations.
• Data modeling strength: excellent relational modeling (Postgres/MySQL), migrations, indexing, query optimization, and data correctness.
• API design excellence: proven ability to design clear, evolvable APIs and contracts across services and external partners.
• High pace + high quality: you thrive in fast-moving environments without sacrificing reliability or security.
• Curiosity and ownership: you enjoy ambiguous problems, learn quickly, and take systems end-to-end (build → ship → operate).

Nice to have

• LLM experience: building product with LLMs (prompting, tool calling, evals, latency/cost tradeoffs).
• Agent architecture familiarity: orchestration patterns, planning/execution loops, memory/state, sandboxed tool execution, human-in-the-loop, safety constraints.
• Framework familiarity: Vercel AI SDK, LangChain/LangGraph, Anthropic Agents SDK, OpenAI tool calling, sandboxing/tool runtimes.