AI Engineer – SC Cleared

Project overview

AI Engineer – SC Cleared

Whitehall Resources require an AI Engineer with SC clearance to work with a key client on a 6 month contract.

*Inside IR35.

*Active SC clearance required.

*Mostly remote working with possible occasional visits to London.

Description

The AI Engineer role will be responsible for working within a Product squad to design, build and deliver GenAI and Agentic AI products.

The individual must have hands-on experience developing production-grade GenAI/Agentic AI solutions using LLMs, RAG and agentic workflow technologies. The role requires strong Python software engineering skills alongside practical experience designing reliable, secure and maintainable AI-enabled applications.

Responsibilities

Technical Scoping & Estimation: Break down product requirements and user stories into technical tasks, provide estimates, identify dependencies, risks and integration requirements, and support delivery planning.

Data Analysis, Engineering & Discovery: Explore and assess structured and unstructured data, identify key data dependencies and quality issues, and prepare, transform and integrate data for use in RAG pipelines, agentic workflows and downstream applications.

Agentic AI Development: Design and implement multi-step Agentic AI workflows using frameworks such as LangGraph, including workflow state, routing, parallel execution, tool use, human-in-the-loop review, checkpointing and recovery.

LLM Application Development: Design and develop LLM-powered application capabilities, including prompt engineering, structured outputs, context management, model configuration and validation of model responses.

RAG & Knowledge Retrieval: Design and implement Retrieval-Augmented Generation solutions, including document ingestion, parsing and chunking, embeddings, indexing, semantic/hybrid search, filtering, reranking and evidence grounding.

AI Evaluation & Assurance: Develop approaches to evaluate LLM and RAG quality, including grounding, retrieval quality, hallucination, output consistency and regression testing. Implement appropriate guardrails, human review, citations, traceability and auditability.

Reliability & Error Handling: Design AI workflows to handle rate limits, timeouts, malformed model outputs, partial failures and other non-deterministic behaviours, including retry, recovery and resumability where required.

Observability & Monitoring: Implement logging, tracing and monitoring across LLM calls, agent workflows and retrieval pipelines to support troubleshooting, performance monitoring, quality assurance and operational support.

Security & Data Access: Ensure AI solutions follow appropriate authentication, authorisation, data access and secure development practices, particularly when integrating agents with enterprise systems and sensitive information.

Testing & Peer Review: Develop automated tests for AI and application components, participate in peer reviews and ensure solutions meet agreed quality, security and engineering standards.

Performance, Cost & Scalability: Consider model selection, token usage, latency, concurrency, retrieval performance and infrastructure cost when designing and optimising AI solutions.

Technical Documentation: Create and maintain documentation covering solution design, workflows, prompts, dependencies, APIs, operational considerations and support requirements.

Collaboration & Communication: Work closely with cross-functional teams, including product managers, BA’s, Product Owners and software and platform engineers, to deliver high-quality AI products

Skills required

Strong Python software engineering experience

Hands-on experience developing GenAI / LLM applications

Hands-on experience designing and implementing Agentic AI workflows

Experience with LangGraph

Strong understanding of LLM workflow design, including state, routing, tools, structured outputs and human-in-the-loop patterns

Practical experience designing and implementing RAG architectures

Experience with document ingestion, chunking, embeddings and vector/semantic search

Experience with prompt engineering and structured LLM outputs

Experience with AI/LLM evaluation, testing and quality assurance

Understanding of guardrails, grounding, hallucination mitigation and AI assurance

Experience building and integrating APIs and backend services

Strong understanding of software engineering principles, automated testing, code review and maintainable application design

Experience handling LLM and agent failure scenarios, retries, error handling and recovery

Understanding of observability and tracing for GenAI/Agentic AI applications

Azure AI & Cloud Services: Hands-on experience building and deploying AI solutions on Azure, including Azure OpenAI, Azure AI Search, Azure AI Foundry, Cosmos DB, Redis, Azure Monitor/Application Insights, Managed Identity and Key Vault.

All of our opportunities require that applicants are eligible to work in the specified country/location, unless otherwise stated in the job description.

Whitehall Resources are an equal opportunities employer who value a diverse and inclusive working environment. All qualified applicants will receive consideration for employment without regard to race, religion, gender identity or expression, sexual orientation, national origin, pregnancy, disability, age, veteran status, or other characteristics.

Project details

• Start: flexible
• Location: London, GB