Software Engineer
Posted 1 week ago by GIOS Technology
Negotiable
Undetermined
Onsite
Sheffield, England, United Kingdom
Summary: The role of Machine Learning Engineer in Sheffield, UK, involves building and maintaining data pipelines for IT knowledge articles and optimizing AI helpdesk responses. The engineer will focus on improving answer quality through various techniques and support model selection and performance benchmarking. This position requires strong collaboration with engineering teams to enhance response quality and reduce failure rates. The role is primarily on-site for three days a week.
Key Responsibilities:
- Build and maintain data pipelines for IT knowledge articles, SOPs, ticket history, and troubleshooting content.
- Develop RAG pipelines, embeddings, indexing, and retrieval optimization.
- Improve answer quality using chunking, ranking, filtering, and grounding techniques.
- Create evaluation datasets and automated quality tests for accuracy, hallucination, and task completion.
- Support model selection, tuning, and performance benchmarking.
- Work with engineering teams to improve response quality and reduce failure rates.
Key Skills:
- Strong Python and data engineering skills.
- Run data quality testing, verify LLM results etc.
- Experience with vector databases, embeddings, and retrieval systems.
- Experience building ETL/data pipelines for structured and unstructured data.
- Understanding of LLM evaluation, experimentation, and model performance metrics.
- Familiarity with SQL, APIs, and cloud data platforms.
- AWS (preferred), GCP exposure.
- Experience with enterprise knowledge systems and ticket datasets.
- Experience with fine-tuning, reranking, or search relevance optimization.
Salary (Rate): undetermined
City: Sheffield
Country: United Kingdom
Working Arrangements: on-site
IR35 Status: undetermined
Seniority Level: undetermined
Industry: IT
We are looking for Machine Learning Engineer at Sheffield, UK – 3 days per week Onsite
Role Summary
Build the knowledge, retrieval, and evaluation layer that allows the AI helpdesk to answer accurately and safely.
Key responsibilities
- Build and maintain data pipelines for IT knowledge articles, SOPs, ticket history, and troubleshooting content.
- Develop RAG pipelines, embeddings, indexing, and retrieval optimization.
- Improve answer quality using chunking, ranking, filtering, and grounding techniques.
- Create evaluation datasets and automated quality tests for accuracy, hallucination, and task completion.
- Support model selection, tuning, and performance benchmarking.
- Work with engineering teams to improve response quality and reduce failure rates.
Required skills
- Strong Python and data engineering skills.
- Run data quality testing, verify LLM results etc
- Experience with vector databases, embeddings, and retrieval systems.
- Experience building ETL/data pipelines for structured and unstructured data.
- Understanding of LLM evaluation, experimentation, and model performance metrics.
- Familiarity with SQL, APIs, and cloud data platforms.
- AWS (preferred), GCP exposure.
Preferred
- Experience with enterprise knowledge systems and ticket datasets.
- Experience with fine-tuning, reranking, or search relevance optimization.