Hybrid Agentic AI Engineer – LLM Systems

Experis UK; Greater London; Hybrid; GBP 70,000 - 110,000; Part time

Benefits offered by this job

Hybrid work model

London office option

Job summary

Experis UK in London seeks an experienced ML/AI Engineer to design, build, and scale agentic LLM systems for production-grade environments. You will collaborate with researchers and engineers to create robust tool-calling, planning, and orchestration frameworks, while integrating multiple LLM providers.

The role emphasizes developing backend services, RAG pipelines, and scalable AI-driven workflows, with a focus on reliability, latency, and cost optimization across enterprise data landscapes.

Qualifications

• 4+ years’ experience in ML/AI engineering.
• Proven hands-on experience building LLM agents, RAG systems, or orchestrated AI workflows in production.
• Strong Python experience.
• Experience with cloud platforms and containerised systems (Docker/Kubernetes) and APIs.

Responsibilities

• Design and build tools, workflows, and infrastructure for agentic LLM systems.
• Develop RAG pipelines, embeddings workflows, and retrieval systems for enterprise data.
• Diagnose and fix failures in agent-generated code and workflows.
• Build frameworks for tool-calling, multi-step planning, orchestration, and agent routing.
• Integrate with LLM providers and support multi-model usage.
• Develop backend services and APIs to support AI-driven applications and workflows.
• Run experiments to improve reliability, latency, cost, and success rates.
• Contribute to evaluation frameworks, observability, and monitoring of performance.

Skills

ML/AI engineering

LLM agents

RAG systems

Python

APIs & microservices

Cloud platforms

Docker & Kubernetes

CI/CD pipelines

Experimentation & metrics

Observability tools

Tools

LangChain

LangGraph

AutoGen

Docker

Kubernetes

Job description

Experis UK in London seeks an experienced ML/AI Engineer to design, build, and scale agentic LLM systems for production-grade environments. You will collaborate with researchers and engineers to create robust tool-calling, planning, and orchestration frameworks, while integrating multiple LLM providers.

The role emphasizes developing backend services, RAG pipelines, and scalable AI-driven workflows, with a focus on reliability, latency, and cost optimization across enterprise data landscapes.