About the Role

We’re looking for a full-stack Agentic AI Engineer who has shipped real agentic systems to production—not demos, not experiments, but systems that run reliably at scale.

You’ll design and build core agentic infrastructure and work directly with leadership on problems that don’t have playbooks yet. This role is for builders who like ambiguity, take ownership, and care deeply about correctness, reliability, and scale.

What You’ll Do

Design and implement agent orchestration systems and multi-agent workflows
Build scalable, reliable agentic systems that work in real-world conditions
Solve infrastructure challenges around execution, concurrency, retries, and failure handling
Own problems end-to-end: architecture → implementation → production deployment
Make hard trade-offs to ship systems that are robust, not fragile

Requirements

Must Have

1.5+ years of hands-on experience building with LLMs and agent frameworks
Production experience with agentic systems (Lyzr, LangChain, LangGraph, CrewAI, Google ADK, Claude Agent SDK, etc.)
Shipped real products or systems that users depend on
High ownership, high agency — you don’t wait to be told what to do

Good To Have

Startup or founding-team experience
Open-source contributions to AI / agent frameworks
Experience at AI-native orgs or fast-scaling startups (ex-YC a plus)

Why Join

Work on unsolved, high-leverage problems in agentic AI
Build infrastructure that could be used by hundreds of thousands to millions of developers
Join a lean, high-ownership team that moves fast and values engineering judgment