Senior AI Engineer

JR United Kingdom; Ipswich; Remote; GBP 100,000 - 130,000; Full time

Job summary

A leading AI solutions provider is looking for a Senior AI Engineer to develop and optimize RAG pipelines and LLM integrations in a remote role. Candidates should have strong Python skills and experience in deploying scalable AI solutions. The position offers a competitive salary and the chance to make a significant impact in AI development.

Qualifications

• 3+ years' experience as a full-stack engineer with strong Python skills.
• Proven track record with LLMs, agentic systems, and RAG pipelines.
• Experience with vector databases, embeddings, and semantic search.

Responsibilities

• Building and optimising RAG pipelines including chunking, embeddings, and vector search.
• Creating full LLM integrations using OpenAI, Hugging Face, and orchestration frameworks.
• Developing robust AI agent systems with tool chaining and multi-step logic.

Skills

Python

LLMs

RAG pipelines

Containerisation

API design

Modern ML deployment tools

Tools

Docker

AWS

OpenAI

Hugging Face

React

Job description

Social network you want to login/join with:

Hiring: Senior AI Engineer (LLMs, Agents, RAG)
Location: Remote (UK or Canada)
Type: Full-time | Permanent
Salary: Up to £130,000 or $240,000 Canadian

Are you passionate about building real AI systems that get used in production? Interested in LLMs, RAG pipelines, and agentic software, with the freedom to make a real impact?

My client are a well-funded early-stage team helping enterprise clients in regulated sectors deploy scalable AI without overhauling their infrastructure. They focus on performance, maintainability, and fast iteration. No fluff, just outcomes. They're now looking for engineers who want to help shape that future.

What You'll Be Working On:

Hiring: Senior AI Engineer (LLMs, Agents, RAG)
Location: Remote (UK or Canada)
Type: Full-time | Permanent
Salary: Up to £130,000 or $240,000 Canadian

Are you passionate about building real AI systems that get used in production? Interested in LLMs, RAG pipelines, and agentic software, with the freedom to make a real impact?

My client are a well-funded early-stage team helping enterprise clients in regulated sectors deploy scalable AI without overhauling their infrastructure. They focus on performance, maintainability, and fast iteration. No fluff, just outcomes. They're now looking for engineers who want to help shape that future.

What You'll Be Working On:

• Building and optimising RAG pipelines including chunking, embeddings, and vector search

• Creating full LLM integrations using OpenAI, Hugging Face, and orchestration frameworks

• Developing robust AI agent systems with tool chaining and multi-step logic

• Building real-time frontend interfaces using React, Next.js, and Vercel AI SDK

• Containerising services using Docker and deploying to AWS (ECS, Lambda)

• Collaborating with researchers to productionise transformer models (e.g. PyTorch, HF)

• Using observability tools like Langfuse to monitor prompt and model performance

• Writing clean, modular, testable code that scales in production environments
  

What They're Looking For:

• 3+ years' experience as a full-stack engineer with strong Python skills

• Proven track record with LLMs, agentic systems, and RAG pipelines

• Experience with vector databases, embeddings, and semantic search

• Solid grasp of prompt engineering and LLM integration best practices

• Familiarity with containerisation, API design, and modern ML deployment tools
  

Bonus if:

• Experience with PyTorch or model fine-tuning

• Open-source contributions to LLM or AI infrastructure tools

• Experience with Elasticsearch or OpenSearch for retrieval

• Familiarity with Terraform, GitHub Actions, or infrastructure automation

• Built doc processing pipelines involving PDFs, HTML, or structured data

• Interest in async workflows and distributed data processing

If you're ready to work on meaningful, high-impact AI problems in a fast-moving team, we'd love to hear from you.

Apply now or drop us a message to chat more.