LLM & AI Features Engineer - Remote (Django/FastAPI)

Django Rest Framework; Greater London; Hybrid; GBP 90,000 - 125,000; Full time

Job summary

Webbyfox is seeking an AI Engineer to design and ship AI-powered features for clients' Python web apps built on Django and FastAPI. You will move LLM ideas from prototype to production, implementing RAG, semantic search, chat assistants, and AI agents with a focus on security and privacy.

You will work with senior Python engineers, integrate multiple LLM APIs, and optimize for latency and cost while maintaining compliance with UK GDPR and best security practices.

Qualifications

• 3+ years of professional Python development experience, incl. production LLM/ML features.
• Hands-on with LLM APIs and frameworks (OpenAI/Anthropic SDKs, LangChain, LlamaIndex).
• Experience with Django or FastAPI and async Python is a plus.

Responsibilities

• Design and ship LLM-powered features for Django/FastAPI apps.
• Integrate LLM APIs (OpenAI, Anthropic, Gemini) and open-source models.
• Build data pipelines for ingestion, embeddings, and vector search.

Skills

Python

Django

FastAPI

LLM APIs

RAG

Vector databases

PostgreSQL

pgvector

LangChain

LlamaIndex

Docker

AWS

GCP

Azure

Pytest

Async Python

Education

Degree in CS/AI or related field

Tools

OpenAI SDK

Anthropic SDK

LangChain

LlamaIndex

Job description

Webbyfox is seeking an AI Engineer to design and ship AI-powered features for clients' Python web apps built on Django and FastAPI. You will move LLM ideas from prototype to production, implementing RAG, semantic search, chat assistants, and AI agents with a focus on security and privacy.

You will work with senior Python engineers, integrate multiple LLM APIs, and optimize for latency and cost while maintaining compliance with UK GDPR and best security practices.