What Youll Do
Build AI Products, Not Just Models
- Design and develop GenAI-powered applications using LLMs, RAG, and agentic workflows
- Translate business problems into measurable AI-driven outcomes
- Define evaluation metrics and product success criteria
Engineer Intelligent Systems at Scale
- Build and optimize retrieval-augmented generation (RAG) pipelines
- Develop agent-based AI systems with tool usage and orchestration
- Deploy solutions on cloud-native architectures (Azure preferred)
Own the AI Lifecycle (GenAI Ops)
- Implement prompt engineering strategies, embeddings, and fine-tuning approaches
- Build evaluation frameworks and guardrails for reliability and safety
- Enable continuous monitoring of quality, latency, and cost
Drive Responsible & Secure AI
- Embed responsible AI practices (bias detection, explainability, moderation)
- Ensure data privacy, governance, and compliance standards
- Build systems aligned with enterprise security and trust principles
Collaborate & influence
- Partner with product, data, and engineering teams to prioritize AI features
- Influence enterprise AI architecture and best practices
- Enable teams through reusable AI components and APIs
What You Bring
Must-Have Skills
- Strong programming in Python and SQL
- Hands-on experience with GenAI patterns: Prompt engineering, Retrieval-Augmented Generation (RAG), Embeddings & semantic search, Agentic workflows
- Experience with AI/ML frameworks: PyTorch / TensorFlow, Hugging Face, LangChain / Semantic Kernel
- Experience deploying AI solutions on cloud platforms (Azure preferred): Azure OpenAI, Azure ML , Azure AI Search
Engineering & Platform Skills
- Strong foundation in data processing (Pandas, NumPy, Spark/Databricks)
- Experience with MLOps / GenAI Ops: MLflow, pipelines, CI/CD, Docker, Azure DevOps
- Experience building APIs and integrating AI into applications
- Understanding of monitoring, observability, and system reliability
Valuable-to-Have
- Experience building ag
📌 Technical AI Product Engineer (Delhi)
🏢 EY
📍 Delhi