- Design, build, and scale end-to-end Generative AI applications for real-world business use cases

- Lead development of GenAI solutions including answering engines, extraction pipelines, and content generation systems

- Architect and deliver RAG-based systems using embeddings, vector databases, retrieval strategies, and caching

- Build and optimize LLM-powered services with a focus on low latency, high throughput, and reliability

- Own GenAI system design across data ingestion, retrieval, inference, and serving layers

- Develop scalable APIs and services using Python and FastAPI

- Collaborate with platform, cloud, and data teams to deploy GenAI systems on AWS or Azure

- Provide technical leadership through design reviews, solution ownership, and mentoring

- Engage with stakeholders on solution design, delivery planning, and technical trade-offs

Must Have :

- Strong hands-on experience in GenAI application development (Q&A systems, extraction, content generation)

- Deep experience building and optimizing RAG pipelines using frameworks like LangChain or LlamaIndex

- Solid understanding of embeddings, vector databases, chunking strategies, retrieval tuning, and caching

- Hands-on experience with LLM platforms such as Azure OpenAI or equivalent

- Strong proficiency in Python with experience building APIs using FastAPI

- Experience designing and scaling GenAI systems for high load and low latency

- Cloud experience with AWS and/or Azure

- Strong prompt engineering skills including contextual prompting, zero-shot, and prompt optimization

- Background in AI/ML, NLP, deep learning, and applied ML engineering

- Ability to own solution architecture and drive end-to-end delivery

Good to Have :

- Experience with agentic AI frameworks such as LangGraph, AutoGen, or CrewAI

- Hands-on exposure to Azure AI ecosystem including Azure ML, Cognitive Services, AKS, ADF/Synapse, and Azure AI Search

- Experience with CI/CD pipelines and LLMOps or MLOps practices

- Advanced GenAI optimization techniques including retrieval tuning, ranking strategies, and inference efficiency

- Experience in technical leadership, client-facing discussions, pre-sales support, or practice building