Description

You will build and deploy products leveraging Large Language Models and agentic workflows.

This role is remote.

Responsibilities

• Build and optimize RAG pipelines using effective embedding, chunking, and indexing strategies.
• Implement agentic workflows using orchestration frameworks like LangChain or Haystack.
• Develop semantic search capabilities using advanced retrieval techniques including HyDE, MMR, and LLM re-ranking.
• Integrate OpenAI APIs and open-source models into production environments.
• Design data structures using vector and graph databases.

Required Skills

• 5+ years of experience in software engineering or related fields.
• Hands-on experience with LLMs and product development.
• Proficiency with OpenAI APIs and open-source models like Llama2, Mistral, and Mixtral.
• Experience with vector databases such as Pinecone or Milvus, and graph databases like Neo4j.
• Working knowledge of LangChain or Haystack frameworks.
• Practical application of HyDE, MMR, and LLM re-ranking for semantic search.
• Experience creating embeddings using MPNET or Ada models.
• Solid understanding of Transformer and Neural Network models.
• Bachelor's degree in any field.

Preferred Skills

• Experience with Chat, IVR, or Banking domains.
• Experience with Speech-to-Text using Whisper or Google TTS.
• Research or hands-on experience with agentic workflows.

Key Skills

Education

Any Gradute