Senior Backend Engineer, Agent Infrastructure

ABOUT AIRBYTE: We’re on a mission to make data available and actionable to everyone, everywhere. With 700+ connectors, our platform powers analytics and gives AI agents the business context they need to do real work. More than 25,000 companies, including 20% of the Fortune 500, rely on Airbyte to put their data to work. We’re built on open source because we believe companies should have full control over their data. A community of 27K members helps shape what we build, and we’re backed by $181M from investors including Benchmark, Accel, Altimeter, Coatue, and Y Combinator. Models keep getting better. What holds AI back is the data informing and shaping its decisions, and that's the layer we're building. We’re just getting started. If you’re excited by big challenges, meaningful ownership, and the chance to help build what’s next, we’d love to meet you. THE ROLE: Airbyte is building the runtime that powers production-grade AI agents. This is not an ML research or prompt engineering role. We’re looking for an experienced backend or platform engineer who has built complex production systems and has also worked hands-on with AI agents, orchestration, retrieval, or LLM-powered applications. Our AI Runtime sits between language models and the enterprise systems agents need to understand and act on. It is responsible for assembling the right context, identifying entities across systems, selecting tools and connectors, coordinating execution, validating evidence, enforcing permissions, and handling failures safely. A user may ask something simple like: - “Investigate this customer and tell me what changed.” Behind that request, the runtime may need to identify the customer across multiple systems, retrieve fresh data, determine which tools to call, coordinate multiple steps, validate the result, and return an answer with evidence the user can trust. That infrastructure is what you’ll help build. We’re still early. The architecture is taking shape, but there is significant room to influence how the runtime is designed, how developers interact with it, and how we make agentic systems reliable in production. WHAT YOU’LL DO: Build the Runtime - Design and implement the orchestration layer that turns natural-language intent into reliable, multi-step execution. - Build systems for routing, state management, retries, failure handling, and long-running agent workflows. - Develop systems for entity resolution, context assembly, connector orchestration, and evidence retrieval. - Build reusable Skills that encapsulate business workflows and domain-specific capabilities. - Coordinate connectors, APIs, tools, deterministic logic, retrieval systems, and multiple language models. Build Reliable AI Infrastructure - Design systems that retrieve and assemble the right enterprise context at runtime. - Build evidence-backed reasoning with citations and traceability that users can inspect and verify. - Implement permission models, freshness validation, and action policies for production environments. - Build evaluation, replay, observability, and debugging systems that help us understand why agents succeed or fail. - Improve the reliability of systems where model outputs may be probabilistic, but execution cannot be. Own Products End to End - Take ambiguous product ideas from prototype through production. - Own features across architecture, implementation, rollout, and iteration. - Work directly with Product, Design, Sales Engineering, Customer Success, and customers to understand real-world problems. - Write high-leverage code that creates reusable infrastructure for future product areas. - Experiment with new agent architectures while maintaining production-grade reliability. WHAT YOU’LL NEED: You may be a strong fit if you are fundamentally a backend or platform engineer who has also spent meaningful time building production AI systems. - 7+ years of software engineering experience building and operating production systems. - Strong backend engineering fundamentals and experience designing distributed systems. - Experience building complex systems involving APIs, asynchronous workflows, concurrency, queues, state, retries, or distributed execution. - Hands-on experience building production applications using LLMs, agents, RAG, tool calling, MCP, or similar technologies. - Experience with orchestration systems, workflow engines, developer platforms, or infrastructure products. - Strong system design skills and the ability to reason about reliability, scale, observability, and failure modes. - Ability to move quickly from prototype to production without sacrificing engineering quality. - Strong product instincts and comfort operating in ambiguous, 0-to-1 environments. - Exceptional written communication skills. - A strong bias toward ownership and shipping. NICE TO HAVE - Experience building agent infrastructure, agent platforms, or evaluation systems. - Familiarity with orchestration technologies such as LangGraph, Temporal, MCP, or similar. - Experience with retrieval systems, vector search, search infrastructure, or knowledge graphs. - Experience building developer tools or platform infrastructure. - Experience with data infrastructure such as Kafka, Iceberg, Postgres, Spark, or modern data warehouses. - Experience working on early-stage products where you helped define architecture and technical direction. WHAT SUCCESS LOOKS LIKE Success is not measured by the sophistication of the prompts. It is measured by whether the runtime becomes more reliable, observable, and trustworthy over time. You’ll build systems that: - Assemble the right context and choose the correct connectors, tools, and Skills. - Execute multi-step workflows reliably. - Recover gracefully when something fails. - Produce evidence-backed answers with citations and traceability. - Enforce permissions, freshness guarantees, and action policies. - Learn from failures through replay, evaluation, and observabili