Machine Learning Engineer

Intelix.AI; Greater London; Hybrid; GBP 90,000 - 150,000; Full time

Job summary

Intelix.AI in London or Manchester offers a hybrid role to build production-grade AI products in a major regulated financial-services environment. The role requires hands-on AI/ML engineers with enterprise delivery experience beyond notebooks and prototypes.

You will design and build production AI, multi-agent systems, RAG pipelines, and tool-layer agents, while integrating with data platforms, implementing guardrails, CI/CD, and collaborating with Risk and Product teams.

Qualifications

• Production AI/ML, LLM, RAG or Agentic AI delivery experience.
• Strong Python and software engineering capability.
• Experience with APIs, microservices and system integration.

Responsibilities

• Design and build production AI, Generative AI and Agentic AI applications.
• Build multi-agent systems with defined roles, handoffs and shared state.
• Develop RAG pipelines, agent workflows and enterprise knowledge integrations.
• Build the tool layer agents with schema validation, retries, timeouts and audit trails.
• Build APIs and services using Python and modern backend frameworks.
• Integrate AI capabilities with internal systems, data platforms and business workflows.
• Implement evaluation, observability, guardrails and human-in-the-loop controls.
• Instrument agent behaviour, covering decision paths, tool-selection accuracy, loop containment and cost per request.
• Support deployment through CI/CD, cloud platforms and containerised environments.
• Work closely with Product Managers, Technical BAs, Architects, Data and Risk teams.
• Contribute to testing, operational readiness and production support.

Skills

Python

APIs

Microservices

Cloud platforms

Production AI/ML

LangChain

Tools

LangGraph

LangChain

Semantic Kernel

AutoGen

CrewAI

Job description

Generative AI | Agentic AI | Multi-Agent Systems | RAG | Production Engineering

Initial 3 months plus extension | London or Manchester | Hybrid, largely remote

We are looking for hands-on AI/ML Engineers to build production-grade AI products inside a major regulated financial-services environment. The requirement is for engineers who have built, integrated, tested and operated enterprise AI in production. Research, notebooks and chatbot prototypes do not cover it.

Key responsibilities

• Design and build production AI, Generative AI and Agentic AI applications
• Build multi-agent systems with defined roles, handoffs and shared state, using planner, executor, validator and router patterns
• Develop RAG pipelines, agent workflows and enterprise knowledge integrations
• Build the tool layer agents act through, with schema validation, retries, timeouts and audit trails
• Build APIs and services using Python and modern backend frameworks
• Integrate AI capabilities with internal systems, data platforms and business workflows
• Implement evaluation, observability, guardrails and human-in-the-loop controls
• Instrument agent behaviour, covering decision paths, tool-selection accuracy, loop containment and cost per request
• Support deployment through CI/CD, cloud platforms and containerised environments
• Work closely with Product Managers, Technical BAs, Architects, Data and Risk teams
• Contribute to testing, operational readiness and production support
• Strong Python and software-engineering capability
• Production AI/ML, LLM, RAG or Agentic AI delivery experience
• Multi-agent orchestration, covering agent handoffs, persistent state, routing and tool invocation
• Familiarity with frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI or similar
• Experience with APIs, microservices and system integration
• Cloud experience across Azure, AWS or GCP
• Understanding of model evaluation, observability, security and governance
• Private-sector delivery experience is essential
• Banking or financial-services experience is highly desirable
• MCP or equivalent tool-interface and integration work
• Evaluation tooling such as RAGAS, LangSmith, golden datasets and regression gates
• Experience operating AI systems under audit, access control and model-risk governance

We are particularly interested in engineers who understand that production AI needs reliability, monitoring, controls and operational ownership. Multi-agent systems raise that bar. They fail in ways single-model systems do not, through hallucinated routing, execution loops, silent tool failures and cost that runs away before anyone notices. The engineers who do well here have seen those failures and built the controls that catch them.