About EY

EY exists to build a better working world, helping to create long-term value for clients, people and society and build trust in the capital markets.

Enabled by data and technology, diverse EY teams in over 150 countries provide trust through assurance and help clients grow, transform, and operate.

Working across assurance, consulting, strategy, tax and transactions, EY teams ask better questions to find new answers for the complex issues facing our world today.

 

Role Summary

 

As an AI Engineer within our internal development team, you will design and implement the intelligence layer of our multi-agent systems. You’ll collaborate with the team members to build, integrate, and deploy secure, performant AI agents powered by LLMs and Retrieval-Augmented Generation (RAG) architectures on Azure.

 

Environment: Azure (OpenAI, ML, Cognitive Search)

 

Key Responsibilities

 

• Develop and maintain LLM- and RAG-based AI agents using Azure OpenAI, LangChain/Semantic Kernel, and Azure ML.
• Collaborate with the Full Stack Developer to integrate agent endpoints into web and backend applications.
• Work with DevSecOps to ensure secure deployment, monitoring, and version control of AI components.
• Implement vector search pipelines (Azure Cognitive Search, FAISS, or Pinecone).
• Optimize model inference for latency, accuracy, and scalability.
• Participate in daily standups, sprint reviews, and code reviews as part of the dev team.

 

Required Skills

 

• 1–2 years’ experience developing AI or NLP applications in Python.
• Hands-on experience with LLMs, prompt engineering (Crafting and optimizing), and RAG design.
• Experience designing RAG pipelines for enterprise search or document intelligence.
• Knowledge of vector databases (e.g., Qdrant, Chroma).
• Knowledge of document chunking, embedding models, and context window optimization.
• Familiarity with metadata-based retrieval and re-ranking strategies.
• Understanding of agent architectures.
• Ability to orchestrate multiple agents for collaborative or role-based tasks
• Strong understanding of transformer architectures (GPT, LLaMA, Mistral, Claude, etc.).
• Experience with LLM fine-tuning and prompt engineering.
• Familiarity with inference optimization, quantization (e.g., bitsandbytes), and deployment techniques.
• Hands-on experience using OpenAI, Hugging Face Transformers, or LangChain.
• Knowledge of model evaluation metrics (e.g., perplexity, hallucination rate, factual consistency).
• Prior experience deploying LLM-based agents or RAG systems in production is a major plus.
• Familiarity with Azure AI Services, Azure ML, Azure Functions, and APIs.
• Understanding of data security, versioning, and MLOps principles.
• Strong collaboration skills within cross-functional agile teams.

 

What working at EY offers

 

• We offer support and coaching, opportunities to develop new skills and progress your career, and the freedom and flexibility to handle your role in a way that’s right for you.
• Continuous learning: You’ll develop the mindset and skills to navigate whatever comes next.
• Success as defined by you: We’ll provide the tools and flexibility, so you can make a meaningful impact, your way.
• Transformative leadership: We’ll give you the insights, coaching and confidence to be the leader the world needs.
• Diverse and inclusive culture: You’ll be embraced for who you are and empowered to use your voice to help others find theirs.

 

 

EY | Shape the future with confidence

 

At EY, we're committed to providing recruitment and career opportunities to all, regardless of gender, sexual orientation, social background or disability.