LLM Engineer - Freelancer

Monterail is building a network of skilled LLM Engineers to design, build, and integrate practical AI features into existing products. This freelance role focuses on delivery and engineering excellence, requiring the ability to integrate AI solutions into production systems using Python, Node.js, or Ruby.

Key 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 like pgvector, Pinecone, or Qdrant.
• Implement safe, reliable LLM endpoints and advise clients on trade-offs regarding latency, accuracy, and cost.

Requirements

• Strong software engineering background in Python, Node.js, or Ruby.
• Hands-on experience integrating LLM APIs into production systems.
• Ability to design pragmatic AI solutions within existing architectures.
• Experience building RAG pipelines, embeddings, and vector search.
• Understanding of cost, latency, and reliability constraints of AI systems.
• Strong communication skills in English, allowing for independent client collaboration.

What we offer

• Opportunity to work on diverse projects within the Monterail Tech Network.
• Flexible freelance collaboration model with part-time or full-time availability.
• Direct impact on shaping AI features for real-world production systems.
• Professional environment focused on pragmatic engineering and delivery.