You can build real agentic AI systems, the kind that actually run in production, power workflows, and get used by real users.
This is a hands-on engineering role focused on designing, shipping, and owning AI agents end-to-end. You'll work on agent architectures, retrieval, evaluation, and production readiness alongside a strong R&D team that values clean engineering and moving fast without cutting corners.
* Strong Python engineering (production-quality code)
* Experience building LLM-powered applications
* Hands-on work with agentic AI systems (planning, tools, memory, multi-step workflows)
* Familiarity with LangChain, LangGraph, LlamaIndex, CrewAI or similar frameworks
* Retrieval systems experience (embeddings, vector databases, hybrid/grounded RAG)
* Evaluation-first mindset (offline datasets, regression tests, monitoring)
* LLMOps / AgentOps experience (tracing, cost & latency, reliability)
* Backend engineering with APIs & services (FastAPI, Postgres, event/workflow systems)
* Production deployment using Docker, Kubernetes, CI/CD
* Cloud experience (AWS, Azure, or GCP)
High trust, high ownership, and space to build things properly. No demo theatre. No endless POCs. Just meaningful AI work at scale.
If you're excited about where applied AI is going and want to be ahead of it let's talk.