Backend Engineer (Python)

Shelf is the operating system for agentic AI: a platform that models your policies, workflows, and operational logic into an AI Data Model so AI agents don't just respond—they reason. The result is AI that understands how your business actually operates and delivers precise, compliant, and auditable outcomes at scale.

Leading enterprises including Amazon, Nespresso, HelloFresh, and KeyBank use Shelf to power AI agents that automate complex workflows, improve operational efficiency, and transform manual processes into intelligent automation.

We're partnered with Microsoft, Salesforce, OpenAI, Snowflake, and Databricks, and have been recognized by Gartner as a Cool Vendor and by IDC as an Innovator for our approach to enterprise AI.

This role is for Middle and Senior backend engineers who can design and own business-critical systems.

We want someone who is strong technically, communicates clearly, and has the judgment to make systems simpler, safer, and easier to evolve over time. Expect real ownership from system design through production.

The team is small enough for engineers to make real decisions. Career growth comes from ownership. Titles matter less than the scope you can carry. The people who grow fastest take responsibility for larger systems, drive customer outcomes, and strive to develop better engineering practices.

You solve ambiguous problems by shaping the right architectural approach, then ship, iterate, and keep it healthy in production.

We build AI-native. Engineers use Codex, Claude Code, and agents they build themselves. We invest in harness engineering through skills, CLIs, logs, traces, and orchestration.

This is a role for someone in a high-growth chapter of their career, who wants to do the best work of their life, learn fast, and win as part of a team going all-in on a hard mission.

• →Build Systems: Design and ship backend services, APIs, data flows, and background processing for production systems.
• →Plan & Execute: Turn vague requirements into concrete technical plans, trade-offs, and execution.
• →Own Production: Own services after launch: reliability, observability, performance, and incident follow-through.
• →Instrument Everything: Instrument what you ship and use production signal to iterate, not just to keep the lights on.
• →Design Well: Make sound decisions around system boundaries, data models, interfaces, and scaling paths.
• →Collaborate: Work closely with product, frontend, and platform engineers to deliver end-to-end outcomes.
• →Improve Engineering: Improve engineering leverage with AI tooling, automation, and internal workflows rather than using AI as a gimmick.
• →Raise the Bar: Raise the quality bar through code review, design review, and pragmatic technical leadership.

• You reliably move important backend work forward without waiting to be tightly managed.
• Your systems are easier to operate and easier to change because of your design decisions.
• You make smart trade-offs to unblock shipping—and you stand by those decisions.
• You keep raising the bar on engineering excellence for yourself and everyone else.

• Backend Experience: Strong senior-level backend engineering experience in production systems.
• Python: Strong Python skills and the ability to design clean, maintainable backend code.
• Systems Thinking: Good distributed systems judgment: concurrency, failure handling, data consistency, async work, and service boundaries.
• Cloud Infrastructure: Hands-on experience with cloud infrastructure such as AWS, GCP, or Azure.
• Databases: Comfort with database schema design and performance tuning for real-time and high throughput scenarios.
• Security: A security-conscious approach to engineering: you build for enterprise-grade requirements, handle sensitive data carefully, and think about the security implications of the systems and AI workflows you ship.
• Ownership: Ability to go from problem statement to design to production rollout with real ownership.
• Communication: Clear written and verbal communication. You can explain systems, trade-offs, and incidents without hiding behind jargon.
• AI-Native: AI-native working style. You already use AI tools in your daily engineering workflow, and you're excited to improve how the team builds, not just your own output: better tooling, workflows, and engineering leverage.

• Experience building agentic systems: AI agents, tool-calling, orchestration, retrieval, or LLM-backed infrastructure in production.
• Working knowledge of TypeScript or the ability to contribute across the stack when needed.
• Experience shaping technical direction for other engineers, even without formal management responsibility.

We care more about ownership, systems judgment, and learning velocity than a perfect keyword match to our stack. If you are the kind of engineer who can take a messy problem and turn it into a strong production system, we want to talk.