Senior Data Engineer

EY; Hyderabad, Bengaluru; Hybrid; INR 2,500,000 - 4,000,000; Full time

Job summary

EY is seeking a Senior Data / ML Engineer to build and scale production-grade AI and agentic systems. The role focuses on turning AI prototypes into reliable, governed production solutions that solve real business problems.

You will deploy LLM-powered apps, design RAG pipelines, and develop end-to-end ML/LLM pipelines with strong Python and scalable systems experience. Collaboration with governance and product teams is essential.

Qualifications

• 6+ years in Data/ML engineering or Applied AI
• Hands-on experience deploying LLM-based systems in production
• Strong Python skills and experience with scalable systems
• Experience with agent frameworks (LangChain, LlamaIndex, AutoGen, CrewAI)
• Knowledge of RAG, vector databases, embeddings, and prompt optimization
• Familiarity with MLOps, monitoring, and cost/performance trade-offs

Responsibilities

• Build and deploy LLM-powered applications and agentic workflows (single & multi-agent).
• Design and implement RAG pipelines, embeddings, and vector search.
• Develop end-to-end ML/LLM pipelines from data ingestion to inference and monitoring.
• Productionize AI systems with cost controls, observability, and guardrails.
• Integrate AI solutions into enterprise workflows and platforms.
• Collaborate with product, platform, and governance teams to deliver responsible AI.

Skills

Python

LLM deployment

Agent frameworks

Tools

LangChain

LlamaIndex

AutoGen

CrewAI

Job description

Key Responsibilities:

Senior Data / ML Engineer (LLM & Agentic Systems)

Were hiring a Senior Data / ML Engineer to build and scale production-grade AI and agentic

systems that solve real business problems. This role is hands-on and engineering-heavy, focused on taking

AI from prototype to reliable, governed production systems.

What Youll Do

• Build and deploy LLM-powered applications and agentic workflows (single & multi-agent).
• Design and implement RAG pipelines, embeddings, and vector search.
• Develop end-to-end ML/LLM pipelines from data ingestion to inference and monitoring.
• Productionize AI systems with cost controls, observability, and guardrails.
• Integrate AI solutions into enterprise workflows and platforms.
• Collaborate with product, platform, and governance teams to deliver responsible AI.

Required Skills and Qualifications:

• 6+ years of experience in Data Engineering, ML Engineering, or Applied AI and should have worked in product development companies
• Hands-on experience deploying LLM-based systems in production.
• Strong Python skills and experience with scalable systems.
• Experience with agent frameworks (LangChain, LlamaIndex, AutoGen, CrewAI, or similar).
• Solid understanding of RAG, vector databases, embeddings, and prompt optimization.
• Familiarity with MLOps, monitoring, and cost/performance trade-offs.

Nice to Have

• Experience in regulated or enterprise environments.
• Exposure to AI governance, explainability, or risk controls.
• Background in document intelligence or NLP-heavy systems.

Why Join

• Build real AI systems, not demos.
• High ownership over architecture and implementation.
• Work on cutting-edge agentic AI with enterprise impact.
• Competitive compensation and strong growth opportunities.