LLM Engineer - Freelancer
At a glance
Mid-level AI Engineering role at Monterail. Remote, Poland.
Pay not stated AI Engineering salary
aimlroles summary, based on the employer's posting.
What you'll do
- Add AI capabilities to existing Python, Node.js or Ruby products, including chat, summaries and document Q&A
- Build retrieval workflows with embeddings and vector search, using tools such as pgvector or Pinecone
- Create dependable LLM endpoints with providers including OpenAI, Anthropic or Azure
- Work directly with clients to shape features, reduce manual work and weigh accuracy, speed and cost
What you bring
- A strong software engineering foundation in Python, Node.js or Ruby
- Practical experience connecting LLM APIs to production systems
- Experience with RAG, embeddings and vector search
- English proficiency at B2 or C1 and availability for fifteen to forty hours weekly
Who this fits
This freelance role suits an independent engineer focused on shipping AI features in production, rather than ML research. Work can be part-time or full-time based on project needs, under a B2B contract. The role is remote in Wrocław, Poland.
From the employer
We're building a network of LLM Engineers who can design, build, and integrate practical AI features into existing products. We're looking for people to collaborate with on a freelance basis - part-time or full-time, depending on project needs.
This role is focused on delivery, not ML research. What matters most is your engineering foundation and your ability to integrate AI into real production systems using Python, Node.js, or Ruby codebases.
Requirements
What we’re looking for
- Strong software engineering background - Python, Node.js, or Ruby
- Hands-on experience integrating LLM APIs into production systems (OpenAI, Anthropic, or similar)
- 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
- Ability to operate independently with clients, take ownership of delivery, and set realistic expectations
- Background in big data or data pipelines is a big plus
- English B2/C1
- Availability of 15-40 hours per week (B2B contract)
What you'll do
- Deliver AI functionality within existing Python, Node.js, and Ruby codebases
- Build LLM-powered features: chat, summaries, classification, smart search, document Q&A
- Design lightweight RAG pipelines using embeddings and vector search
- Leverage vector DBs (pgvector, Pinecone, Qdrant)
- Implement safe, reliable LLM endpoints (OpenAI, Anthropic, Azure)
- Collaborate directly with clients to shape AI features and reduce manual effort
- Advise clients when NOT to use AI and navigate trade-offs around latency, accuracy, and cost
What do we mean by freelance?
- Read more at Monterail Tech Network