Python Engineer

Ncounter; City Of London; On-site; GBP 60,000 - 95,000; Full time

Job summary

Ncounter is expanding its AI engineering capability and seeks a Python Engineer to build production-grade, LLM-powered backend services. You’ll design APIs with FastAPI, implement robust data flows with PostgreSQL, and push models into secure, scalable deployments powered by Docker and Kubernetes.

Experience turning exploration into reliable, observable systems is essential. You will work with multidisciplinary teams to translate operational problems into practical AI solutions, focusing on

Qualifications

• 5+ years' commercial Python engineering experience, including production backend systems.
• Strong FastAPI, REST API, async Python, PostgreSQL and SQL experience.
• Demonstrable experience integrating LLMs into real applications, not just experiments.

Responsibilities

• Engineer Python backend services and APIs using FastAPI and asynchronous development patterns.
• Design and integrate LLM capabilities using OpenAI, Azure OpenAI or comparable foundation models.
• Build practical RAG, enterprise search and document intelligence solutions using embeddings and vector databases.
• Develop prompt strategies while managing production considerations including latency, cost, retries and rate limits.
• Explore agentic workflows and LLM orchestration using LangChain or similar frameworks.
• Work with consultants and customer stakeholders to translate operational problems into practical AI solutions.
• Improve security, testing, observability and reliability across deployed applications.

Skills

Python

Async programming

Software architecture

Tools

FastAPI

PostgreSQL

Docker

Kubernetes

CI/CD

pytest

OpenAI/Azure OpenAI

Job description

Python Engineer

Ncounter is working with a technology consultancy expanding its AI engineering capability across major law enforcement and public sector transformation programmes. We are looking for an experienced Python Developer who has moved beyond experimenting with Generative AI and has genuine experience engineering LLM-powered solutions for production environments.

Working within multidisciplinary consulting teams, you will help organisations explore how AI can improve complex operational processes, information discovery and decision support. You will take ideas from discovery and prototype stages into secure, reliable services, working alongside architects, consultants and frontend engineers.

What you'll be doing:

• Engineer Python backend services and APIs using FastAPI and asynchronous development patterns
• Design and integrate LLM capabilities using OpenAI, Azure OpenAI or comparable foundation models
• Build practical RAG, enterprise search and document intelligence solutions using embeddings and vector databases
• Develop prompt strategies while managing production considerations including latency, cost, retries and rate limits
• Explore agentic workflows and LLM orchestration using LangChain or similar frameworks
• Work with consultants and customer stakeholders to translate operational problems into practical AI solutions
• Improve security, testing, observability and reliability across deployed applications

What we're looking for:

• 5+ years' commercial Python engineering experience, including production backend systems
• Strong FastAPI, REST API, async Python, PostgreSQL and SQL experience
• Demonstrable experience integrating LLMs into real applications, rather than purely personal or experimental projects
• Strong Docker, Kubernetes/OpenShift, CI/CD and pytest knowledge
• Experience working with large codebases and improving existing services safely
• Knowledge of Azure, RAG, pgvector, Chroma, FAISS, Entra ID, OAuth/OIDC, Redis, Terraform, Prometheus or OpenTelemetry would strengthen your application.

Current or recently held SC clearance is required.