Senior AI Engineer

We are seeking a AI Engineer to transition our AI capabilities from "prototype" to "production." In this role, you will not just experiment with models; you will architect robust Agentic Systems that can plan, reason, and execute complex workflows autonomously for a wide variety of business user needs while experimenting with cutting-edge models and tools to push the boundaries of what’s possible. The ideal candidate is a forward-thinking engineer who thrives on hands-on experimentation with AI models and frameworks, learns quickly, and is naturally curious. You will collaborate closely with product managers, business partners, and platform teams to deliver high-value AI agents that solve real-world problems across the enterprise. Client is a leading multi-brand technology solutions provider to business, government, education and healthcare customers in the United States, the United Kingdom and Canada. A Fortune 500 company and member of the S&P 500 Index, Client was founded in 1984 and employs approximately 10,000 coworkers. For the trailing twelve months ended September 30, 2020, the company generated Net sales over $18 billion. Requirements - Bachelor’s degree with 5+ years of software engineering experience, including AI/ML exposure, or 9+ years of software engineering experience with AI/ML exposure. - Strong hands-on Python experience for AI/LLM application development. - Proven experience designing and building AI agents and Agentic AI solutions. - Experience integrating LLM APIs, such as OpenAI, Azure OpenAI, Anthropic, or Gemini. - 2+ years of hands-on LLM development, with experience in LangChain/LangGraph, vector databases such as Pinecone, Weaviate, or pgvector, and advanced prompt engineering techniques. - Strong production mindset, including experience handling rate limits, context limitations, and non-deterministic LLM behaviour. - Excellent communication and documentation skills, with the ability to explain AI concepts to non-technical stakeholders and support knowledge sharing across teams. Responsibilities - Design and implement complex multi-agent workflows, including agent orchestration, state management, human-in-the-loop flows, and tool/function calling. - Build secure tool integrations connecting AI agents with internal APIs, databases, and enterprise platforms. - Develop production-grade RAG and retrieval pipelines, optimising vector search, document processing, chunking, and re-ranking. - Establish data quality practices and collaborate with Data Engineering teams to prepare reliable datasets for AI agents. - Build LLMOps and evaluation capabilities, including automated testing, LLM-as-a-Judge, safety checks, and quality monitoring within CI/CD. - Implement observability and tracing to monitor agent behaviour, latency, failures, and production performance. - Optimise LLM performance and costs through prompt optimisation, caching, and token usage management. - Prototype emerging AI technologies and turn successful solutions into scalable, maintainable production systems. - Evaluate and help establish standards for agent connectivity and emerging AI technologies.