EY Global Delivery Services (GDS) is seeking a Senior AI Automation Engineer to design, build, and refine enterprise-grade AI automation solutions for a global clientele. This role focuses on hands-on engineering expertise to enhance AI systems, boost model performance, and deliver scalable, production-ready AI automation.

You will operate under architectural guidance, taking ownership of critical solution components, leading small project teams, and delivering impactful AI solutions within consulting engagements. The position demands a robust combination of software engineering, applied AI, optimization methodologies, and secure development practices.

The ideal candidate will independently implement and optimize AI-driven systems, contribute to developing reusable accelerators, and mentor junior engineers within a client-facing consulting setting. This role offers the chance to shape your career with global scale and support, contributing to a better working world.

Key responsibilities include designing, developing, and optimizing AI-driven automation using LLMs, agent frameworks, and orchestration platforms. You will own and execute end-to-end implementation of solution components, integrating them into enterprise systems and CI/CD pipelines.

Optimize AI systems for latency, cost, accuracy, and scalability, including caching, batching, and prompt tuning. Develop and enhance Retrieval-Augmented Generation (RAG) pipelines, focusing on chunking, retrieval tuning, re-ranking, and embeddings. Implement and refine fine-tuning strategies, covering dataset preparation, prompt tuning, and model evaluation.

Build and productionize agentic systems with frameworks like LangGraph, AutoGen, or CrewAI. Develop automated evaluation frameworks, benchmarking pipelines, and performance metrics. Contribute to AI harness frameworks, reusable accelerators, and enterprise AI development standards. Lead workstreams, client discussions, and POCs. Mentor junior engineers and ensure engineering quality. Collaborate with architects on scalable implementations and uphold secure coding and AI security best practices.

A Bachelor’s degree in Computer Science, Engineering, AI/ML, Cybersecurity, or a related field is required, along with 4–8 years of experience in software engineering, AI/ML, or automation engineering. Strong hands-on experience in implementing and optimizing AI/LLM-based solutions is essential, as is prior experience in client-facing consulting environments.

Proficiency in Python is a must, with exposure to JavaScript and TypeScript. Experience with AI/LLM developer tools like OpenAI Codex or GitHub Copilot is expected, alongside familiarity with AI frameworks such as LangChain or LlamaIndex, and cloud platforms like Azure, AWS, or GCP.

Candidates should possess skills in AI platforms (e.g., Azure OpenAI, Hugging Face), vector databases (e.g., Pinecone, FAISS), and observability tools (e.g., LangSmith, PromptLayer). DevOps and CI/CD experience with tools like GitHub Actions or Azure DevOps is also necessary. Familiarity with core concepts like RAG optimization, prompt engineering, embeddings, model fine-tuning, and agentic workflows is crucial.

Preferred cyber experience includes application security (secure coding, SAST/DAST, DevSecOps) or offensive security (VAPT, red teaming). Strong analytical skills, team leadership capabilities, effective client interaction, and the ability to thrive in fast-paced consulting environments are vital. Preferred certifications include Microsoft Azure AI Engineer Associate or AWS Machine Learning Specialty.