AI/ML Engineer

Role Overview

Own the AI/chatbot intelligence layer — integrating and optimizing LLM APIs to deliver accurate, fast, and cost-efficient conversational experiences to millions of users.

Responsibilities

• Integrate and manage LLM APIs (Claude/OpenAI) for chatbot conversation logic
• Design and refine prompts for accuracy, safety, and brand tone
• Build RAG (Retrieval Augmented Generation) pipelines for domain-specific knowledge
• Monitor and optimize AI API costs at high scale without compromising quality
• Set up evaluation frameworks to test chatbot response quality
• Work closely with backend team on latency and reliability of AI responses

Requirements

• Practical experience integrating LLM APIs (OpenAI, Anthropic, or similar) in production
• Strong understanding of prompt engineering and RAG architecture
• Experience with vector databases (Pinecone, Weaviate, or similar)
• Python proficiency; familiarity with LLM orchestration frameworks (LangChain, LlamaIndex)
• Understanding of cost-performance tradeoffs when serving AI at scale

Skills

• Python
• LangChain
• OpenAI
• RAG
• Pinecone

Nice to Have

• Experience fine-tuning or evaluating LLMs
• Background in NLP/conversational AI systems
• Experience with multilingual chatbot support (Hindi/Marathi/regional languages)

Benefits

• Health insurance
• Work from home