Build the Future of
Autonomous AI

The Role

We're looking for an engineer who thinks in terms of agent loops, tool orchestration, and emergent system behaviors. You'll architect and build autonomous AI pipelines that don't just respond to prompts — they reason, plan, execute multi-step workflows, and self-correct when things go sideways.

This isn't wrapper engineering. You'll be designing agentic architectures that coordinate multiple foundation models, manage complex state machines, implement reflection and critique loops, and build the scaffolding that turns raw LLM capabilities into reliable, production-grade autonomous systems.

What You'll Do

• Design multi-agent systems that decompose complex tasks across specialized model instances
• Build robust tool-use frameworks with structured outputs, error recovery, and graceful degradation
• Implement self-critique and iterative refinement loops that improve output quality
• Architect memory and context management systems for long-running agent sessions
• Develop observability and debugging tools for non-deterministic AI systems
• Push updates to production multiple times per week — we ship fast

You Might Be a Fit If...

• You've built systems where the AI does more than answer questions — it executes
• You understand the difference between ReAct, Plan-and-Execute, and Tree-of-Thoughts — and when to use each
• You've wrangled the chaos of non-deterministic systems into reliable, testable software
• You read AI research papers for fun (or at least, for work-fun)
• You're comfortable with Python, TypeScript, or both — we're flexible on stack

Our Stack