Staff Backend Engineer, Agent Infrastructure

Airbyte • San Francisco, CA

2d • $250,000 - $280,000 • Onsite

About The Position

Airbyte is hiring a Staff Backend Engineer for its Agent Infrastructure team, which incubates product opportunities at the intersection of data, AI, and developer infrastructure. The role is for an experienced backend or platform engineer who has built complex production systems and has hands-on experience with AI applications or infrastructure. It is not an ML research or prompt engineering position. The engineer will own technical explorations, build prototypes, and take promising ideas into production, with significant influence over technical direction and product development.

The work spans infrastructure that lets AI agents configure Airbyte, troubleshoot syncs, and access data from connected sources and warehouses; search and retrieval over enterprise data; systems for defining and maintaining semantic models; and stateful SaaS replicas for developing and testing agents. The engineer will explore product hypotheses, work with customers and cross-functional teams, evaluate technical approaches, and build reliable, observable backend systems, APIs, and infrastructure. They will own architecture and execution from design through rollout and iteration, lead technical decisions across teams, and communicate priorities, risks, and tradeoffs.

Success means taking promising ideas from prototype to products customers use, improving infrastructure through real-world usage and feedback, and making technical decisions that make systems more reliable and easier for other teams to build on. The position is onsite in San Francisco, California, four days per week.

Requirements

• At least 10 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 and shipping AI-powered products 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 ability to reason about reliability, scale, observability, and failure modes.
• Demonstrated ability to lead technical direction across teams and influence architectural and engineering decisions.
• 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 Haves

• Experience building and operating AI agents in production, including debugging, observability, and evaluation.
• Experience building agent infrastructure, agent platforms, or evaluation systems.
• Experience with retrieval systems, vector search, search infrastructure, or semantic models.
• Experience building developer tools, platform infrastructure, or integrations with third-party SaaS APIs.
• Experience with data infrastructure such as Kafka, Iceberg, Postgres, Spark, or modern data warehouses.

Responsibilities

• Turn product hypotheses into focused technical experiments and prototypes that test feasibility and expose constraints.
• Work with customers, Product, Design, and customer-facing teams to understand real-world problems and incorporate feedback into technical decisions.
• Evaluate competing technical approaches and use findings to influence product direction.
• Design and implement backend systems, APIs, and infrastructure for AI, data, and developer products.
• Build reliable, observable systems with clear failure handling, debugging, and operational safeguards.
• Take promising prototypes into production and improve them based on usage, incidents, and customer feedback.
• Own architecture and execution across technical design, implementation, rollout, and iteration.
• Lead technical decisions spanning teams; align interfaces and dependencies and influence architecture beyond immediate projects.
• Communicate priorities, risks, and tradeoffs clearly and follow through on commitments.
• Build infrastructure for AI agents to configure Airbyte, troubleshoot syncs, and access data from connected sources and warehouses.
• Build and operate search infrastructure for retrieval over enterprise data, improving relevance, latency, and production reliability.
• Develop systems for defining and maintaining semantic models over enterprise data.
• Build realistic, stateful SaaS replicas for developing and testing agents, including reproducing API behavior, failures, and state changes.
• Help take new ideas from prototype to production and improve them through customer feedback and real-world usage.
• Use technical experiments and engineering judgment to improve product and architecture decisions.

Benefits

• Flexible PTO, with a culture that encourages at least 25 days off annually.
• 16 weeks of fully paid parental leave for all parents.
• Comprehensive medical, dental, and vision coverage for employees and dependents.
• 401(k) retirement plan.
• Professional development budget, conference sponsorship, and book reimbursement.
• Commuter benefits and monthly internet reimbursement.
• Breakfast and lunch in the San Francisco office.
• Collaborative, in-person culture focused on learning, growth, and impact.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed