Genai Python Engineer Needed - Sheffield (Hybrid) - Inside IR35

GenAI Python Engineer

Location: Sheffield - Hybrid, 3 days per week onsite required

Contract: Inside IR35

Duration: 6 - 12 Months Rolling Contract

We are looking for an experienced GenAI Python Engineer with strong hands‑on experience building end‑to‑end Generative AI and RAG applications within enterprise environments.

The successful candidate will be responsible for integrating data from multiple systems, extracting and parsing information from documents and images, working with structured databases, storing content within vector databases, building robust retrieval pipelines, and ensuring solution quality through evaluation frameworks and ground‑truth validation.

Key Responsibilities

• Design and build enterprise GenAI and RAG‑based applications using data from multiple systems.
• Integrate structured and unstructured data sources, including databases, APIs, files and document repositories.
• Develop pipelines for extracting and parsing data from documents and images using OCR and document intelligence tools.
• Process, structure, chunk and prepare extracted content for AI use cases.
• Store and manage parsed content, embeddings and metadata within vector databases.
• Build and optimise retrieval pipelines covering chunking, indexing, metadata tagging, filtering and reranking.
• Work with relational and enterprise databases for querying and data enrichment.
• Implement GenAI evaluation practices covering accuracy, groundedness, relevance, hallucination detection and response quality against ground truth.
• Build scalable APIs, services and production‑grade AI workflows.
• Work closely with architects, platform teams and business stakeholders.
• Follow enterprise standards for security, governance, observability and performance.

Mandatory Skills & Experience

Candidates must have strong experience in the following:

• Very strong Python development skills.
• Strong hands‑on experience in AI/ML engineering and Generative AI applications.
• Proven experience building RAG applications in enterprise environments.
• Strong knowledge of document parsing, OCR and image‑based data extraction.
• Experience with LLM orchestration frameworks and prompt design.
• Experience with vector databases, embeddings and semantic search.
• Experience implementing retrieval techniques including chunking, indexing, metadata tagging, filtering and reranking.
• Experience working with SQL and/or NoSQL databases and enterprise data integration patterns.
• Understanding of GenAI evaluation frameworks, benchmark datasets and ground‑truth‑based validation.
• Experience assessing AI outputs for accuracy, groundedness, relevance, hallucinations and overall response quality.
• Experience building scalable APIs/services and production‑grade AI workflows.
• Ability to independently build GenAI applications across the full life cycle, from data ingestion and extraction through to retrieval and evaluation.

Bonus/Preferred Skills

The following would be beneficial but are not mandatory:

• Experience with the Azure AI technology stack.
• Experience processing high volumes of documents.
• Familiarity with enterprise architecture, security and compliance controls.
• Exposure to AI monitoring, model evaluation and observability tools.

Ideal Profile

You will be a practical, hands‑on engineer who is comfortable working across AI engineering, data engineering and application integration.

You should be capable of independently designing and delivering production‑grade GenAI solutions from ingestion through to retrieval, evaluation and deployment.

Please note: This role requires onsite attendance in Sheffield 3 days per week and is inside IR35.