Back to all roles
Agentic AI

RAG Engineer

We're seeking an exceptional RAG Engineer to build and scale production AI systems for our portfolio of Series A–C companies. You'll work on cutting-edge AI infrastructure, ship features that directly impact product velocity, and help define what great AI engineering looks like in a growth-stage context.

📧 Email your resume tohr@thehirehare.com

What you'll do.

  • 🔍 Design and implement production RAG systems with vector databases (Pinecone, Weaviate, Qdrant, Chroma, pgvector)
  • 📝 Build intelligent chunking strategies, embedding pipelines, and retrieval algorithms optimized for accuracy and speed
  • 🔗 Architect hybrid search systems combining semantic search, keyword matching, and graph-based retrieval
  • 🎯 Implement reranking models, context compression, and retrieval evaluation frameworks (hit rate, MRR, NDCG)
  • ⚡ Optimize embedding models and vector index performance at scale (HNSW, IVF, quantization)
  • 📊 Build comprehensive monitoring and observability for retrieval quality, latency, and relevance metrics

What we're looking for.

Requirements

  • 3+ years of production experience building and shipping AI/ML systems (or 5+ for senior roles)
  • Strong programming skills in Python and experience with modern AI frameworks (PyTorch, TensorFlow, JAX)
  • Deep understanding of LLMs, transformers, and the latest AI research
  • Production experience with cloud infrastructure (AWS, GCP, Azure) and containerization (Docker, Kubernetes)
  • Strong systems thinking — you understand trade-offs between accuracy, latency, cost, and reliability
  • Growth-stage experience preferred — you thrive in fast-moving, ambiguous environments

Nice to have

  • Open-source contributions or published research in AI/ML
  • Experience working at an AI-first company or research lab
  • Familiarity with the latest AI tools, frameworks, and models
  • Strong writing and documentation skills
  • Experience mentoring or leading junior team members

🛠️ Tech stack.

Python, TypeScript
Vector DBs: Pinecone, Weaviate, Qdrant, Chroma, pgvector
Embedding Models: OpenAI, Cohere, Voyage, BGE, E5
LangChain, LlamaIndex, Haystack
FAISS, Annoy, HNSW, ScaNN
Elasticsearch, PostgreSQL
Docker, Kubernetes, AWS/GCP

Interested in this role?

📧 Send your resume tohr@thehirehare.com