Text
#vacancy #remote #freelance #AIengineer #LLM #RAG #LangGraph
Senior AI Engineer (LLM / RAG / Agents) - Freelance, Remote
We build AI solutions for enterprise clients. Our systems run on self-hosted infrastructure: open-source LLMs, on-premises servers and private cloud.
We are looking to connect with senior freelance engineers for upcoming client projects and potential long-term collaboration.
What you will do
Design and build production RAG systems and AI agents
Run open-source LLMs self-hosted, from model selection to serving and optimization
Build retrieval pipelines: document parsing, chunking, embeddings, hybrid search and reranking
Make systems reliable: evaluation, guardrails, monitoring and hallucination control
Deploy on Kubernetes together with our DevOps engineers
Work directly with client teams, from requirements to production rollout
Must have
4+ years of professional Python development, at least one AI/LLM system in production
Hands-on experience with LangChain and/or LangGraph
Vector databases such as pgvector or Qdrant
Experience with self-hosted LLMs (e.g. vLLM, Ollama, TGI)
Docker and basic Kubernetes
English at B2 level or higher
Working hours overlapping with UTC+0 to UTC+4
Registered as self-employed or with your own company, able to issue invoices
Nice to have
RAG evaluation (RAGAS, Langfuse or similar)
TypeScript / Node.js / React or Java
On-premises or private cloud deployments
What we offer
Challenging AI projects that help you deepen your expertise and grow your technical skills
Opportunities to work with modern AI technologies and solve real-world engineering problems
Long-term collaboration opportunities
Fully remote work
A small, experienced team that values engineering quality
How to apply
Please send :
Your CV and LinkedIn/GitHub
A short description of one AI system you built: the problem, the architecture, your personal role and what went wrong along the way (5-10 sentences)
Your daily rate in EUR (net) and earliest start date
Your country of residence and where your business is registered
Our process: A short intro call to get to know each other. For specific project opportunities, we conduct a live technical session in which we discuss and debug a real RAG scenario together.
We verify the location of all applicants. Applicants based in Russia or Belarus cannot be considered.
Ready to apply? Drop us a message on Telegram: @hidden