AI Data / RAG Specialist

We are looking for an **AI Data / RAG Specialist** to build and manage retrieval-based AI systems using internal company data. You will design scalable pipelines that enable accurate, context-aware responses powered by modern AI architectures. **Key Responsibilities** * Build and maintain RAG (Retrieval-Augmented Generation) pipelines * Process, clean, and index structured/unstructured data * Generate and manage embeddings for efficient retrieval * Integrate vector databases and retrieval systems * Ensure high relevance and accuracy of AI-generated responses * Optimize systems for speed, scalability, and performance **Required Skills** * Strong understanding of RAG architecture and embeddings * Experience with vector databases and retrieval systems * Data preprocessing and structuring skills * Proficiency in Python and backend fundamentals **Tools \& Technologies** **Vector Databases:** Pinecone, Weaviate, FAISS **AI/LLM Platforms:** OpenAI, Google Gemini, Hugging Face **Frameworks:** LangChain, LlamaIndex **Backend \& Data:** Python, APIs, JSON, ETL pipelines **Storage:** AWS S3, PostgreSQL, MongoDB **KPIs** * Retrieval accuracy * Response relevance score * Query latency (response time) Job Types: Full-time, Fresher, Internship Contract length: 3-6 months Pay: ₹20,000\.00 - ₹40,000\.00 per month Work Location: In person