Staff Backend Engineer, Agent Infrastructure

Airbyte, Inc.; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Flexible PTO

Parental leave

Medical coverage

401(k)

Professional development

Commuter benefits

Office meals in SF

Job summary

Airbyte is building data tooling that enables AI-powered workflows and enterprise data access. We are seeking an experienced backend/platform engineer with hands-on AI experience to own explorations, prototypes, and production readiness for critical systems.

You will own architecture, lead technical direction, and collaborate with Product and Design to deliver reliable, observable infrastructure that scales as we expand our connector ecosystem and data workloads.

Qualifications

• 10+ years of software engineering experience building and operating production systems.
• Strong backend fundamentals and distributed systems design.
• Experience with APIs, asynchronous workflows, concurrency, queues, state, retries, or distributed execution.
• Hands-on experience shipping AI-powered products using LLMs, agents, RAG, tool calling, MCP, or similar tech.
• Experience with orchestration systems, workflow engines, developer platforms, or infrastructure products.
• Strong system design skills focusing on reliability, scale, observability, and failure modes.
• Ability to lead technical direction across teams and influence architecture decisions.
• Ability to move quickly from prototype to production without sacrificing quality.
• Excellent written communication skills and ownership mindset.

Responsibilities

• Build backend infrastructure and APIs for AI, data, and developer products.
• Design reliable, observable systems with strong failure handling and operational safeguards.
• Take prototypes to production and iterate based on usage and feedback.
• Own architecture and execution across design, implementation, rollout, and iteration.
• Lead cross-team technical decisions and align interfaces and dependencies.

Skills

Backend engineering

Distributed systems

APIs

Asynchronous workflows

Concurrency

Observability

AI-powered products

Leadership

Architectural decisions

Strong communication

Job description

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 of 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 incubating new product opportunities at the intersection of data, AI, and developer infrastructure. Our small team builds tooling and infrastructure for data practitioners and software engineers, leveraging Airbyte's foundation in enterprise connectivity.

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 applications or infrastructure. You'll own technical explorations, build prototypes, and take promising ideas through to production.

We're still early. Some of our work extends existing products, while other projects begin as hypotheses that need validation. There's significant room to influence technical direction, challenge assumptions, and help shape what we build next.

What You'll Work On

• Airbyte MCP: Build infrastructure that lets AI agents configure Airbyte, troubleshoot syncs, and access data directly from connected sources and warehouses. Design reliable, secure, and observable interfaces across the connector ecosystem.
• Semantic Search & Retrieval: Build and operate search infrastructure for high-quality retrieval over enterprise data. Improve relevance, latency, and reliability in production.
• Semantic Models: Develop systems for defining and maintaining semantic models over enterprise data. Help AI applications use consistent business definitions and produce answers that can be verified against underlying data.
• SaaS Sandbox: Build realistic, stateful replicas of SaaS systems for developing and testing agents. Reproduce API behavior, failures, and state changes so workflows can be evaluated without using production accounts.

What You'll Do

Explore New Product Opportunities

• Turn product hypotheses into focused technical experiments. Build prototypes that test feasibility and expose important constraints.
• Work directly 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 what you learn to influence product direction.

Build Production-Grade Infrastructure

• 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.

Lead Technical Direction

• Own architecture and execution across technical design, implementation, rollout, and iteration.
• Lead technical decisions that span teams. Align interfaces and dependencies, and influence architecture beyond your immediate projects.
• Communicate priorities, risks, and tradeoffs clearly, and follow through on commitments.

What You'll Need

You may be a strong fit if you are fundamentally a backend or platform engineer who has shipped AI-powered products.

• 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 the 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 Have

• 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.

What Success Looks Like

Success is not measured by the number of prototypes we build. It is measured by whether we turn promising ideas into products customers use and infrastructure they can depend on.

You'll help us:

• Take new ideas from prototype to production and improve them through customer feedback and real-world usage.
• Build reliable, observable systems that are easier to operate, debug, and improve over time.
• Use technical experiments and engineering judgment to make better product and architecture decisions.
• Lead technical decisions that make systems simpler, more reliable, and easier for other teams to build on.

Location

• San Francisco, CA — onsite 4 days/week

Why You'll Love Working at Airbyte:

At Airbyte, we believe great work happens when people feel supported, trusted, and empowered to grow. Our market-leading Total Rewards package is designed to help you thrive professionally and personally. Our benefits and perks include:

• Flexible PTO with a culture that encourages at least 25 days off annually
• 16 weeks 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 our San Francisco office
• A collaborative, in-person culture focused on learning, growth, and impact

If you find this role exciting, we encourage you to apply even if you think you don’t meet all of the requirements!

We are not accepting agency submissions or recruiting firm support for this role. Unsolicited resumes will not be considered.

Airbyte is an equal opportunity employer that does not discriminate on the basis of actual or perceived race, creed, color, religion, national origin, ancestry, age, physical or mental disability, pregnancy, genetic information, sex, sexual orientation, gender identity or expression, marital status, familial status, domestic violence victim status, veteran or military status, or any other legally recognized protected basis under federal, state or local laws. Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

Airbyte is committed to providing reasonable accommodations for qualified individuals with disabilities in our job application procedures. Please let us know if you need assistance or accommodations due to a disability.