Machine Learning Engineer

Machine Learning Engineer

Location: Sheffield (3 days on-site per week) Rate: £500 per day

About the Role

We're looking for a skilled Machine Learning Engineer to help build and optimise the intelligence layer behind an AI-powered helpdesk. In this role, you'll focus on enabling accurate, safe, and high-quality responses by developing robust knowledge retrieval and evaluation systems.

You'll play a key part in designing data pipelines, improving retrieval performance, and ensuring AI outputs meet high standards for accuracy and reliability.

Key Responsibilities

• Build and maintain data pipelines for IT knowledge articles, SOPs, ticket history, and troubleshooting content
• Develop and optimise RAG (Retrieval-Augmented Generation) pipelines, including embeddings, indexing, and retrieval strategies.
• Improve AI response quality through chunking, ranking, filtering, and grounding techniques
• Create evaluation datasets and implement automated testing for:

• Accuracy
• Hallucination detection
• Task completion

• Support model selection, tuning, and performance benchmarking
• Collaborate with engineering teams to enhance response quality and reduce failure rates

Required Skills & Experience

• Strong Python and data engineering expertise
• Experience building ETL/data pipelines for structured and unstructured data
• Solid understanding of:

• Vector databases, embeddings, and retrieval systems
• LLM evaluation and experimentation frameworks
• Model performance metrics and validation techniques

• Experience running data quality testing and validating LLM outputs
• Proficiency with SQL, APIs, and cloud data platforms
• Hands-on experience with AWS (preferred) and exposure to GCP

Desirable Experience

• Experience working with enterprise knowledge systems and ticket datasets
• Familiarity with:

• Fine-tuning models
• Re-ranking techniques
• Search relevance optimisation

Why Join?

• Work on cutting-edge AI and LLM-driven systems
• Opportunity to shape the intelligence layer of a real-world AI product
• Collaborative, forward-thinking engineering environment
• Competitive day rate and flexible hybrid working model

#4794863 - Ashley

• Strong Python and data engineering expertise
• Experience building ETL/data pipelines for structured and unstructured data
• Solid understanding of:

• Vector databases, embeddings, and retrieval systems
• LLM evaluation and experimentation frameworks
• Model performance metrics and validation techniques

• Experience running data quality testing and validating LLM outputs
• Proficiency with SQL, APIs, and cloud data platforms
• Hands-on experience with AWS (preferred) and exposure to GCP

Desirable Experience

• Experience working with enterprise knowledge systems and ticket datasets
• Familiarity with:

• Fine-tuning models
• Re-ranking techniques
• Search relevance optimisation

• Opportunity to shape the intelligence layer of a real-world AI product
• Collaborative, forward-thinking engineering environment
• Competitive day rate and flexible hybrid working model

#4794863 - Ashley