Description

You will build and deploy generative AI products powered by Large Language Models, focusing on agentic workflows and semantic search.

This role is on-site.

Responsibilities

• Build and deploy products using LLMs and Agentic Workflows.
• Implement semantic search using HyDE, MMR, and LLM reranking.
• Manage data retrieval using Vector and Graph databases.
• Develop speech-to-text integrations using Whisper or Google TTS.

Required Skills

• 5+ years of professional experience.
• Hands-on experience with OpenAI APIs and open-source models (Llama2, Mistral, Mixtral).
• Proficiency with LangChain and Haystack frameworks.
• Experience with Vector Databases (Pinecone, Milvus).
• Experience with Graph Databases (Neo4j).
• Strong understanding of Transformer and Neural Network models.
• Practical application of HyDE, MMR, and LLM reranking.
• Experience creating embeddings with MPNET and Ada.

Preferred Skills

• Domain experience in Chat, IVR, or Banking.

Key Skills

Education

Any Graduate