Staff ML Engineer: Agentic AI & Production RAG Systems

WeDoTech; Greater London; Hybrid; GBP 148,000 - 221,000; Full time

Job summary

WeDoTech in London is seeking a senior hands-on Staff Engineer to design and scale production AI/ML systems, driving adoption of Agentic AI across engineering teams and establishing reusable patterns. You will shape architectures for reliable AI delivery in regulated environments.

The role centers on robust RAG and retrieval architectures, LangGraph/LangChain patterns, monitoring, guardrails and governance, plus CI/CD and MLOps for high-complexity use cases.

Qualifications

• Deep experience with Python and strong software engineering fundamentals.
• Production ML/AI engineering experience.
• Experience with agentic AI and LLM-based applications.
• Experience with Retrieval Augmented Generation (RAG).
• Experience with LangChain and/or LangGraph.
• Experience with vector databases and retrieval.
• Experience with MLOps and production deployment.
• Experience with AI evaluation, testing and observability.
• Experience with AI governance, model risk and engineering controls.
• Experience with ML frameworks such as PyTorch, TensorFlow or Scikit-learn.
• Experience operating in complex, regulated or high-risk environments would be valuable.

Responsibilities

• Design robust, production-grade AI and ML systems.
• Drive adoption of Agentic AI across multiple engineering teams.
• Define reusable engineering standards, architectures and implementation patterns.
• Design and evolve production RAG and retrieval architectures.
• Establish effective LangGraph/LangChain patterns for agentic applications.
• Improve AI evaluation, testing, observability and production monitoring.
• Develop guardrails, controls and approaches to hallucination and model risk.
• Support the move towards high-risk and high-complexity AI/ML use cases.
• Establish best practice across MLOps, CI/CD and deployment.
• Influence senior engineers and technical stakeholders without direct line management.
• Help engineering teams use AI-assisted development tools effectively within their workflows.

Skills

Python

ML Engineering

Agentic AI

LLM Applications

RAG

LangChain/LangGraph

Vector Databases

MLOps

AI Evaluation & Observability

AI Governance & Risk

ML Frameworks (PyTorch/TF/Sklearn)

Tools

AWS

LangChain/LangGraph

CI/CD

Job description

WeDoTech in London is seeking a senior hands-on Staff Engineer to design and scale production AI/ML systems, driving adoption of Agentic AI across engineering teams and establishing reusable patterns. You will shape architectures for reliable AI delivery in regulated environments.

The role centers on robust RAG and retrieval architectures, LangGraph/LangChain patterns, monitoring, guardrails and governance, plus CI/CD and MLOps for high-complexity use cases.