Senior AI Engineer

As a Senior AI Engineer, you'll design, build, and improve the backend and infrastructure layer behind advanced AI products.

You'll work across:

• LLM-powered applications
• Retrieval-Augmented Generation systems
• AI agents and workflow orchestration
• Vector search and embedding pipelines
• GraphRAG
• Prompt engineering and structured outputs
• Model evaluation, optimisation, and monitoring
• Scalable APIs and production backend systems
• AI infrastructure on AWS

This role is suited to someone who understands that strong AI engineering is not just about calling a model API. It is about building the surrounding systems that make AI reliable: retrieval, orchestration, evaluation, observability, latency management, cost control, and fault tolerance.

Responsibilities

• Design and build production-grade LLM applications and AI-powered backend services.
• Develop and optimise RAG pipelines, including ingestion, chunking, embeddings, retrieval, reranking, and response generation.
• Build AI agents and workflows that can use tools, call APIs, handle state, and operate within clear reliability constraints.
• Create scalable APIs and backend services using Python and FastAPI or similar frameworks.
• Work with vector databases, PostgreSQL, Redis, and cloud-native infrastructure.
• Integrate LLM providers, embedding models, orchestration frameworks, and evaluation pipelines.
• Improve system performance across latency, cost, throughput, reliability, and model quality.
• Build evaluation frameworks for LLM outputs, including golden datasets, regression tests, human review loops, and production monitoring.
• Make architecture decisions around AI infrastructure, backend design, observability, and deployment.
• Own features and systems from design through to production operation.
• Collaborate closely with product, engineering, and leadership teams to turn ambiguous AI product ideas into robust technical systems.

Do you have experience in Python?, Do you have a Master's degree?, We're looking for senior-level engineers with strong production experience.

You should have:

• Strong commercial experience building and operating production backend systems.
• Excellent Python engineering skills.
• Experience with FastAPI, Flask, Django, or similar backend frameworks.
• Hands-on experience building LLM applications, RAG systems, AI agents, or AI workflow platforms.
• Strong understanding of AWS services. Azure experience is also acceptable.
• Experience with Docker and ideally Kubernetes.
• Experience with PostgreSQL and Redis.
• Experience with vector databases such as pgvector, Pinecone, Weaviate, Qdrant, Milvus, OpenSearch, or similar.
• Practical knowledge of prompt engineering, structured outputs, tool calling, model evaluation, and model optimisation.
• Familiarity with LangChain, LlamaIndex, Semantic Kernel, Haystack, or similar frameworks.
• Good engineering judgement around reliability, testing, observability, security, and maintainability.

Nice-to-Have Skills

• Experience in a startup, scale-up, or high-growth technology environment.
• Experience building AI products used by real customers or internal teams at scale.
• Experience with agentic systems, workflow state, retries, guardrails, and traceability.
• Experience optimising LLM workloads for token usage, latency, caching, model routing, and cost.
• Experience with open-source models, fine-tuning, embeddings, or model deployment.
• Experience with queues, async processing, event-driven systems, or distributed backend architectures.
• Strong product sense and the ability to balance technical depth with delivery speed.

• Salary: £95,000-£110,000 depending on experience.
• Permanent, full-time role.
• High ownership and autonomy.
• The chance to work on cutting-edge AI systems in production.
• Direct impact on technical architecture and product direction.
• A strong engineering culture with low bureaucracy and high trust.
• Opportunity to work across LLM applications, AI infrastructure, backend systems, and applied AI product development.
• A team that values practical technical judgement over hype.

Hiring Process

The process is designed to be focused and respectful of senior candidates' time:

• Introductory conversation
• Technical discussion focused on production experience, architecture, and AI systems
• Practical technical/task discussion or system design exercise
• Final conversation with leadership
• Offer

Who This Role Is For

This role is for a senior engineer who wants to build serious AI systems - not demos, not wrappers, and not fragile prototypes.

You should be comfortable with ambiguity, capable of owning systems end-to-end, and excited by the challenge of building AI products that are reliable, measurable, scalable, and genuinely useful.

If you've built production systems and now want to work at the frontier of applied AI engineering, this is the kind of role worth exploring.

Interested? Apply or reach out for a confidential conversation.

Pay: £95,000.00-£250,000.00 per month

This is a hands-on senior engineering role for someone who has built real systems in production - not just prototypes, notebooks, or API wrappers. You'll work on AI systems that need to be reliable, observable, scalable, and useful in real-world environments. About the Company We are a high-growth technology company building modern AI products that combine strong backend engineering with the latest advances in LLMs, retrieval, agents, and AI workflow orchestration. The engineering culture is pragmatic, technical, and ownership-driven. We care about clean architecture, production reliability, fast iteration, and measurable impact. You'll be joining a team that gives senior engineers real autonomy: the ability to shape architecture, make technical decisions, own systems end-to-end, and work on AI products that are actively used in production.