Remote AI Engineer: LLM, RAG & Vector Search for Python

Python Software Foundation; Greater London; Remote; GBP 85,000 - 110,000; Full time

Benefits offered by this job

Remote work allowed

Flexible hours

Job summary

Webbyfox is a UK-based Python web development agency seeking an AI Engineer to design, build, and ship AI-powered features for Python web applications using Django and FastAPI. You will move LLM ideas from prototype to production, integrating retrieval-augmented generation, embeddings, and vector searches.

Collaborate with senior Python engineers and client teams to deliver secure, scalable AI features, and optimize performance and costs through caching and model selection.

Qualifications

• 3+ years of professional Python development experience, including at least 1 year building LLM or ML features used in production.
• Hands-on experience with LLM APIs and frameworks (e.g. OpenAI/Anthropic SDKs, LangChain, LlamaIndex, or similar)
• Solid understanding of RAG architectures, embeddings, and vector databases (pgvector, Pinecone, Weaviate, Qdrant, or similar)
• Experience building APIs with FastAPI or Django; async Python is a plus
• Strong PostgreSQL skills; pgvector experience is a plus
• Familiarity with prompt engineering, tool/function calling, and agent design patterns
• Experience evaluating and monitoring LLM output (eval frameworks, tracing, observability tools)
• Working knowledge of Docker, cloud platforms (AWS, GCP, or Azure), and CI/CD
• Good testing discipline with pytest
• Understanding of AI safety, data privacy, and responsible AI practices
• Clear communication skills and the ability to explain AI trade-offs to non-technical clients
• Nice to have: experience with ML fundamentals (PyTorch, Hugging Face, fine-tuning), Wagtail, or open-source contributions
• Degree in Computer Science, AI/ML, or a related field, or equivalent practical experience

Responsibilities

• Design and build LLM-powered features such as retrieval-augmented generation (RAG), semantic search, chat assistants, and AI agents.
• Integrate LLM APIs and open-source models into Django and FastAPI services.
• Build and maintain data pipelines for document ingestion, chunking, embeddings, and vector search.
• Engineer prompts, tool and function calling, and multi-step agent workflows.
• Set up evaluation, testing, and monitoring for AI features, covering quality, latency, cost, and safety.
• Optimise performance and cost through caching, model selection, and batching.
• Make sure AI features are secure, privacy-conscious, and compliant with UK GDPR.
• Work with clients in discovery sprints to find practical, high-value AI use cases.
• Keep up with the fast-moving AI ecosystem and share knowledge across the team

Skills

Python development

LLM/ML feature development

Prompt engineering

API design

Testing (pytest)

Data privacy & AI safety

Clear communication

Education

Degree in Computer Science or related field

Tools

FastAPI

Django

OpenAI/Anthropic SDKs

LangChain

LlamaIndex

pgvector

Pinecone

Weaviate

Qdrant

Docker

AWS

GCP

Azure

CI/CD

PyTorch

Hugging Face

Job description

Webbyfox is a UK-based Python web development agency seeking an AI Engineer to design, build, and ship AI-powered features for Python web applications using Django and FastAPI. You will move LLM ideas from prototype to production, integrating retrieval-augmented generation, embeddings, and vector searches.

Collaborate with senior Python engineers and client teams to deliver secure, scalable AI features, and optimize performance and costs through caching and model selection.