Design, build, and maintain production-grade LLM pipelines (RAG, prompts, orchestration)
Develop AI features in Jeeves core products: spend categorization, docs, anomaly detection
Implement structured output validation, fallbacks, and confidence scoring
Evaluate AI frameworks/tools (LangChain, LlamaIndex, OpenAI, Anthropic) and pick best tools
Establish prompt versioning and evaluation as models/data evolve
Design and maintain vector search pipelines (Pinecone, Weaviate, pgvector) for semantic search

🎯 Requirements

Bachelor's degree in CS/Engineering or equivalent
5+ years software engineering; 3+ AI/ML in production
Hands-on with LLM-powered apps using OpenAI/Anthropic/Cohere
RAG pipelines with embeddings and vector DBs (Pinecone/Weaviate/pgvector)
Strong Python; familiarity with LangChain or LlamaIndex
ML model serving: REST/gRPC endpoints, validation, latency, monitoring

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot