Data Scientist

RAG Development: Build and optimize sophisticated Retrieval Augmented Generation (RAG) systems utilizing LangChain, Llama Index, and other relevant tools. Generative Model Development: Design, train, and fine-tune advanced generative models, including language models and image generators, using frameworks like OpenAI models (e.g., GPT-3, DALL-E 2), Llama models, and Hugging Face models. LLM Ops: Oversee LLM operations, encompassing model selection, fine-tuning, and deployment. API Development: Develop robust REST APIs using Python and FastAPI to expose generative AI capabilities to internal and external clients. Microservices Architecture: Design, implement, and maintain scalable and maintainable microservices-based systems for generative AI applications. Full Stack Development: Contribute to full-stack development, including frontend and backend components, to create comprehensive generative AI solutions. Web Development: Develop user-friendly web applications and interfaces to interact with generative AI models. Azure AI Services: Leverage Azure AI services, such as Azure AI Search and Azure AI Studio, to accelerate development and deployment. Vector Databases: Work with open-source vector databases and tools like Langchain & Llama Index to efficiently store and retrieve embeddings for semantic search and retrieval tasks. Database Interactions: Design, develop, and maintain efficient data pipelines and schemas for storing and retrieving large-scale datasets. Agentic LLM Development: Explore and develop agentic LLMs that can exhibit goal-oriented behavior and interact with the environment autonomously. Agentic RAG: Integrate agentic LLMs into RAG systems to enable more sophisticated and context-aware responses. Advanced RAG: Implement advanced RAG techniques, such as semantic search, query expansion, and document summarization, to improve the quality and relevance of generated responses.