| Description: |
Senior GenAI / AI Engineering Consultant Contract: Initial 3-Month Contract
Rate: Up to £500 per day (Inside IR35)
Location: Remote with occasional travel to client site
Start Date: ASAP Overview We are supporting a major organisation undertaking a large-scale AI and document intelligence transformation programme. They are seeking an experienced Senior GenAI / AI Engineering Consultant to design and deliver enterprise-grade Generative AI solutions within a highly regulated environment. This is a hands-on role requiring experience building production-ready GenAI applications rather than proof-of-concept solutions. You will work across LLM architecture, RAG frameworks, document intelligence, vector search, and AWS cloud-native AI services. Key Responsibilities - Design and implement production-scale GenAI and LLM-powered solutions.
- Build Retrieval Augmented Generation (RAG) architectures for document-heavy use cases.
- Develop document processing pipelines capable of extracting and validating information from complex PDFs, scanned documents, and regulatory records.
- Design multi-agent workflows incorporating extraction, validation, routing, scoring, and human-in-the-loop review processes.
- Implement semantic and hybrid search solutions using Amazon OpenSearch vector search capabilities.
- Establish evaluation frameworks for AI-generated content, including accuracy, precision, recall, confidence scoring, and hallucination detection.
- Work closely with compliance, security, and business stakeholders to ensure governance and regulatory requirements are met.
- Develop production-quality Python applications and support CI/CD deployment pipelines.
Essential ExperienceGenerative AI & LLMs - Proven experience designing and deploying production GenAI solutions.
- Experience building end-to-end LLM pipelines processing real customer documents at scale.
- Strong understanding of hallucination detection, output validation, confidence scoring, and model evaluation.
RAG Architecture - Experience designing Retrieval Augmented Generation solutions in document-intensive environments.
- Knowledge of chunking strategies, embedding model selection, retrieval optimisation, and cross-document reasoning.
- Experience defining and measuring retrieval quality metrics.
Document Intelligence & NLP - Delivery experience extracting structured information from unstructured and semi-structured documentation.
- Experience working with PDF documents, scanned files, regulatory submissions, and compliance documentation.
- Strong understanding of data quality controls and validation frameworks.
AWS & Foundation Models - Hands-on experience with Amazon Bedrock and foundation models such as Claude.
- Experience implementing prompt engineering, guardrails, safety controls, and model benchmarking.
- Strong AWS development experience using Python and Boto3.
Vector Databases & Search - Experience implementing semantic search solutions using Amazon OpenSearch Service.
- Knowledge of:
- Vector indexing and embedding storage
- k-NN search configuration
- Hybrid search (keyword + semantic)
- Performance optimisation for large-scale retrieval workloads
Software Engineering - Strong Python development experience within production environments.
- Experience with:
- LangChain
- LlamaIndex
- LangGraph or CrewAI
- AWS SDK (Boto3)
- PyPDF
- Amazon Textract
- Unstructured.io
- Experience implementing CI/CD pipelines and deployment automation.
Governance & Regulated Environments - Experience delivering solutions within highly regulated sectors such as financial services.
- Understanding of:
- PII handling
- Data classification frameworks
- Audit and traceability requirements
- Information security controls
- Risk and compliance governance
 |
