LLM Engineer Freelancer

Role overview

Monterail is building a network of freelance LLM Engineers to design, build, and integrate practical AI features into existing production products. The work is delivery-focused (not ML research), collaborating on part-time or full-time B2B engagements depending on project needs.

Responsibilities

• Add AI functionality into existing Python, Node.js, and Ruby codebases
• Build LLM-powered features such as:
  • chat, summaries, classification
  • smart search and document Q&A
• Design lightweight RAG pipelines using embeddings and vector search
• Work with vector databases including pgvector, Pinecone, and Qdrant
• Implement safe and reliable LLM endpoints (OpenAI, Anthropic, Azure)
• Work directly with clients to shape AI features and reduce manual effort
• Advise clients on when not to use AI and manage trade-offs around latency, accuracy, and cost

Requirements

• Strong software engineering background in Python, Node.js, or Ruby
• Hands-on experience integrating LLM APIs into production systems (e.g., OpenAI, Anthropic, or similar)
• Ability to design pragmatic AI solutions within existing architectures
• Experience building RAG pipelines, including embeddings and vector search
• Understanding of cost, latency, and reliability constraints for AI systems
• Ability to work independently with clients and set realistic expectations
• English B2/C1

Nice to have

• Background in big data or data pipelines

Hiring / engagement

• Freelance (B2B), part-time or full-time depending on project needs