Vector Search & LLM Specialist

Role Overview: You are an AI Architect who will be responsible for designing and implementing cutting-edge generative AI systems with a focus on Retrieval-Augmented Generation (RAG). Your role involves connecting large language models to data sources to ensure accurate, contextual, and valuable responses from the AI system. Key Responsibilities: - Design and implement RAG architectures combining large language models with knowledge bases - Optimize vector search for quick retrieval of relevant information - Manage vector databases and develop indexing strategies - Create and refine prompts for models like GPT-4 and Claude - Process and manage large datasets for AI system consumption - Fine-tune and customize models to meet specific needs - Plan system integrations for seamless operation - Benchmark performance and plan for scalability as user base grows Qualifications Required: - Comfortable working with Large Language Models from providers like OpenAI and Anthropic - Familiarity with vector databases such as Pinecone, Weaviate, or PGVector in Postgres - Proficiency in embedding models and techniques - Knowledge of RAG frameworks like LangChain and LlamaIndex - Experience with vector search libraries including FAISS - Proficient in deep learning frameworks such as PyTorch or TensorFlow - Understanding of distributed computing for handling larger workloads Additional Details: You will have the opportunity to work at the forefront of AI, combining the latest Large Language Models with knowledge retrieval to enhance the AI system's understanding and response to user needs. Your contributions will play a crucial role in making the AI system more helpful, accurate, and trustworthy. If you have 4-6 years of experience in working with RAG models and are enthusiastic about pushing the boundaries of AI capabilities, this role is perfect for you. Apply now to be part of building the future of AI! (Note: In-person work location in Bangalore, Full-time job type),