What You’ll Do

• Design and implement agentic AI workflows using Python and our orchestration platform.
• Build and optimize RAG pipelines with embeddings, vector databases (Milvus, Qdrant, etc.), and model APIs.
• Develop intelligent data access layers that connect enterprise systems with LLMs and reasoning agents.
• Collaborate with backend, DevOps, and data teams to bring production-grade AI services to life.
• Experiment with open-source models, fine-tuning, and evaluation tools to drive practical innovation.

What We’re Looking For

• Strong Python programming skills (experience with LangChain, LangGraph, or similar a plus).
• Hands-on understanding of LLMs, embeddings, or multi-agent architectures.
• Experience integrating AI with databases, APIs, or cloud infrastructure.
• Passion for turning cutting-edge AI research into practical, reliable enterprise features.
• Clear communicator who thrives in a fast-moving, collaborative, fully-remote environment.
• Familiarity with RAG pipelines, vector databases, and model observability tools.

Nice-to-Have

• Understanding of enterprise-grade deployment (Kubernetes, Docker, Helm).
• Experience optimizing inference cost, latency, or security in production AI systems.

Why Join Us

• Work at the frontier of agentic and generative AI, shaping the systems enterprises actually use.
• Build open-source components that make AI adoption safer and faster.
• Fully remote, flexible environment with a focus on impact over bureaucracy.