AI Engineer

About the Role

This position is for a client company: a VC-backed Artificial Intelligence startup that has successfully raised $400K USD in funding. Join us to build and own production-grade AI systems, including RAG pipelines, advanced AI agents, scalable chatbots, and robust evaluation frameworks.

What You'll Do

• Own the intelligence layer: Build RAG and retrieval systems that synthesize data from multiple sources to ensure every AI output is relevant and grounded in real context. Develop research agents, enrichment agents, and follow-up sequencing workflows.
• Evaluate Performance: Construct evaluation frameworks to measure output quality before it reaches users. Define what 'good' means for your specific use cases and build infrastructure to measure consistency.
• Drive Reliability: Work with frontier models, vector databases (e.g., Pinecone, Milvus), and agent libraries like LangGraph to improve retrieval accuracy and agent reliability at scale without human intervention.

Your Qualifications

• 3+ years of hands-on experience shipping AI/ML systems in production environments (no demos or prototypes).
• Deep expertise building RAG pipelines, including chunking strategies, embedding models, and re-ranking techniques.
• Proven track record of deploying chatbots that run reliably in production.
• Strong knowledge of the current AI tooling landscape: LLMs, frameworks (LangChain/LangGraph), vector DBs, and agent orchestration libraries.

Why Join Us?

Take ownership of meaningful product decisions from day one at a funded startup. Accelerate your career with outsized responsibility while building scalable solutions in a high-growth environment.