We are looking for a Generative AI Engineer to design and develop advanced AI-driven solutions that leverage Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) pipelines. This role involves building scalable, high-performance GenAI applications such as answering engines, content authoring tools, and extraction components, while ensuring optimal user experience and system efficiency.
Key Responsibilities
- Develop GenAI Applications: Build intelligent solutions like Q&A; engines, content generation systems, and data extraction tools.
- Design RAG Pipelines: Implement and optimize RAG-based architectures using frameworks such as LangChain and LlamaIndex.
- Integrate LLMs: Work with models like Azure OpenAI and other LLMs to deliver business-specific outcomes.
- Prompt Engineering: Craft and refine prompts using contextual and zero-shot strategies to guide LLMs effectively.
- System Components: Implement essential engineering components including Vector Databases, caching layers, chunking, and embeddings.
- Scalability & Performance: Scale applications to support high user traffic, large datasets, and low-latency responses.
- API Development: Design and deploy scalable APIs using frameworks like FastAPI.
- Collaborate with cross-functional teams for end-to-end product development and deployment.