Production ML Engineer – LLM Pipelines & RAG (UK)

WyserAI; United Kingdom; Hybrid; GBP 70,000 - 110,000; Full time

Job summary

Wyser is seeking a skilled Machine Learning Engineer to help ready and support models from inception to production. The role involves designing, deploying and maintaining ML pipelines, with a focus on LLM applications, RAG systems and integration with Azure services.

You will collaborate with product, engineering and data science teams to translate domain requirements into robust ML behavior, working in a fast-paced, innovative environment in the UK.

Qualifications

• Minimum 2 years shipping ML/AI features in production.
• Experience in R&D or product engineering environments.
• Strong Python production services experience.

Responsibilities

• Design, implement and optimize ML model pipelines end-to-end.
• Develop and deploy LLM applications and RAG systems.
• Integrate third-party AI services (Gemini, speech APIs, Azure Doc Intelligence).
• Establish evaluation loops and release gates for accuracy.
• Collaborate with product, engineering and data science to translate requirements into ML behavior.

Skills

Python production

LLM app engineering

RAG systems

Azure cloud

Git & Docker

Vector databases

Tools

FastAPI

pytest

Gemini

QDrant

Docker

Azure Blob Storage

Job description

Wyser is seeking a skilled Machine Learning Engineer to help ready and support models from inception to production. The role involves designing, deploying and maintaining ML pipelines, with a focus on LLM applications, RAG systems and integration with Azure services.

You will collaborate with product, engineering and data science teams to translate domain requirements into robust ML behavior, working in a fast-paced, innovative environment in the UK.