AI Native Builder/Architect

Overview

Join Atlan's team building its context layer, the agent platform and vertical agents that run on it. You will take undefined problems to production systems fast, owning initiatives with one or two people alongside you.

What you'll do

• Own a 0→1 initiative from problem to production: frame it, write the spec when there isn't one, pick the architecture and build it.
• Build agents with the people who own the outcome, inside Atlan or at a customer, scoping workflows and placing agents where the work already happens.
• Earn autonomy with evidence: start with shadow runs, study the misses and widen what the agent can do as results support it.
• Design for failure, deciding what happens when a tool is down, context is thin or the agent is unsure, and how a person takes over.
• Make engineering calls on deterministic code versus model use, build vs. reuse, model choice, cost and reliability, and explain the trade-offs.
• Make agent behavior observable by tying traces and evals to the revision that ran, tracking consistency, cost and latency alongside success rate, and treating drift as a regression.
• Build on and extend the context layer, agent platform and registry: versioned skills, layered instructions, explicit permissions for tools and secrets, and model changes handled as migrations with evals rerun before promotion.
• Build AI-native yourself: run coding agents on your own work, keep their skills and instructions up to date, and review what they write for architectural drift.
• Share what you learn by turning what works into skills, reference architectures and quality gates that others adopt, and by demoing what you've built.

What you'll need

• Hands-on experience building software systems and shipping 0→1 products or platforms into production, often without a spec.
• Experience shipping agents or LLM systems that real people use, and tracing failures back to the context, tool call or decision that caused them.
• Experience using evals to find and fix real problems, checking what a score actually counts, and judging agents by user impact such as hours saved, error rate or cycle time.
• Experience designing for failure first: what the agent may touch, what happens when it is wrong, and where a person approves before it acts.
• Experience building with coding agents every day and holding what they write to the same bar as your own code.
• A critical-optimist mindset: you believe what agents can do is real and test what still fails before trusting them with more.
• First-principles reasoning: when a familiar design doesn't fit, or a better model makes old scaffolding unnecessary, you notice and rebuild.
• Strong systems judgment for production reliability, latency, cost and security, and leaving systems in a shape others can build on.
• Comfort doing your best work owning an initiative with one or two people alongside you, without a large team.

Nice to have

• Experience with MCP, A2A, agent frameworks and runtimes, LLM gateways or agent observability, or having built an agent harness or orchestration layer.
• Experience with knowledge graphs, vector search, retrieval or semantic layers.
• Having built an eval suite from scratch, or run shadow evaluations, LLM grading or staged rollouts.
• Having shipped agents that write to a system of record, with permissions, approvals and an audit trail.
• Having led AI adoption inside an engineering or business team and being able to show the before and after.
• Founding-engineer, technical-founder or early-stage startup experience where you built something from nothing.
• A public trail of work, such as repos, demos, write-ups or talks, that shows how you build.

Details

• Remote-first, work from anywhere; the team spans 15+ countries.
• Trust-first, asynchronous environment.