GenAI RAG Specialist

Responsibilities

Custom LLM Development: Design and fine-tune models for specific use cases.

RAG Chatbots: Build intelligent chatbots leveraging vector search and external data sources.

Vector Embeddings: Create and optimize embeddings for semantic search with vector databases (e.g., Pinecone, FAISS).

Optimizations: Perform fine-tuning, compression, and latency optimization for scalable models.

Project Delivery: Lead end-to-end AI solution development.

Requirements

Programming: Expert in Python (PyTorch, TensorFlow, Hugging Face).

GenAI Expertise: Strong knowledge of LLMs, RAG, and generative AI.

Experience: 45 successful projects in RAG, fine-tuning, and embeddings.

Skills: Vector databases, deployment frameworks (Docker, Kubernetes), cloud platforms (AWS, GCP).

Communication: Excellent written and verbal skills.