EY Global Delivery Services (GDS) is searching for a seasoned AI Automation Engineer – Senior. This role is pivotal in designing, developing, and optimizing enterprise-grade AI automation solutions for a global clientele. You will leverage deep hands-on engineering expertise to enhance AI systems, boost model performance, and deliver scalable, production-ready AI-enabled automation.

While working under architect guidance, you will take ownership of key solution components, lead small workstreams, and deliver impactful AI solutions across various consulting engagements. The position demands a strong combination of software engineering, applied AI, optimization techniques, and secure development practices. The ideal candidate is adept at independently implementing and optimizing AI-driven systems, contributing to reusable accelerators, and mentoring junior engineers within a client-facing consulting framework.

- Design, develop, and refine AI-driven automation solutions leveraging LLMs, agent frameworks, and orchestration platforms. - Take end-to-end ownership of solution component implementation, including seamless integration into enterprise systems and CI/CD pipelines. - Enhance AI systems by optimizing latency, cost, accuracy, and scalability through methods like caching, batching, and prompt refinement. - Develop and improve Retrieval-Augmented Generation (RAG) pipelines, focusing on chunking strategies, retrieval tuning, re-ranking, and embedding optimization. - Implement and optimize fine-tuning strategies, covering dataset preparation, prompt tuning, and model evaluation workflows. - Build and productionize agentic systems using leading frameworks such as LangGraph, AutoGen, CrewAI, or Semantic Kernel. - Create automated evaluation frameworks, benchmarking pipelines, and comprehensive model performance metrics. - Contribute to AI harness frameworks, reusable accelerators, and establish enterprise AI development standards. - Lead small workstreams, manage client discussions, deliver compelling demos, and execute proof-of-concept (POC) implementations. - Mentor and review the work of junior AI Automation Engineers, ensuring high engineering quality and adherence to best practices. - Collaborate closely with architects to translate high-level designs into robust, scalable implementations. - Ensure strict adherence to secure coding practices, DevSecOps principles, and AI security best practices.

We are seeking a candidate with a Bachelor’s degree in Computer Science, Engineering, AI/ML, Cybersecurity, or a related field. A minimum of 4 to 8 years of experience in software engineering, AI/ML, or automation engineering is required, with strong hands-on experience in implementing and optimizing AI/LLM-based solutions.

Prior experience working in client-facing consulting environments is essential. Proficiency in Python is a must, with exposure to JavaScript or TypeScript being beneficial. Candidates should be skilled in AI/LLM tools and frameworks such as LangChain, LlamaIndex, LangGraph, AutoGen, or Semantic Kernel. Experience with cloud platforms like Azure, AWS, or GCP, and vector databases such as Pinecone or Azure AI Search is expected.

Familiarity with observability and evaluation tools (e.g., LangSmith, PromptLayer) and DevOps/CI/CD practices (e.g., GitHub Actions, Azure DevOps) is highly valued. A strong understanding of core concepts including RAG optimization, prompt engineering, embeddings, model fine-tuning, evaluation frameworks, and agentic workflows is critical for success in this role. Excellent analytical and problem-solving abilities, coupled with effective communication and client interaction skills, are key attributes we are looking for.