Lead Data Scientist

Job Summary

We are looking for an experienced Generative AI / LLM Engineer with 8–13 years of experience to design, develop, and deploy enterprise-grade AI applications. The ideal candidate will have strong hands-on expertise in Python, LLMs, RAG, LangChain, LangGraph, Agentic AI, vector databases, and AI application development.

The candidate will work closely with engineering and product teams to build scalable, reliable, and production-ready AI solutions using the latest Generative AI technologies.

Key Responsibilities

• Design and develop LLM-powered applications and Agentic AI systems.
• Build and implement production-grade RAG pipelines for document and knowledge retrieval.
• Develop AI agents and multi-step workflows using LangChain and LangGraph.
• Develop AI services, APIs, and backend components using Python.
• Write, optimize, and manage SQL queries for data retrieval and processing.
• Integrate LLMs such as GPT, Claude, Gemini, or equivalent models into enterprise applications.
• Implement embeddings, vector databases, semantic search, prompt engineering, and context management.
• Develop tool-calling and workflow-based agent systems and integrate external APIs/services.
• Evaluate and improve AI solutions for accuracy, relevance, latency, scalability, and reliability.
• Deploy, monitor, troubleshoot, and maintain AI applications in production environments.
• Collaborate with engineering, product, and business teams to translate requirements into scalable AI solutions.
• Stay updated with emerging developments in Generative AI, LLMs, Agentic AI, and AI engineering practices.

Required Skills

• 8–13 years of overall software/technology experience, with significant hands-on experience in AI/ML and Generative AI.
• Strong proficiency in Python.
• Hands-on experience with LLMs / Generative AI.
• Strong understanding and practical experience with RAG architecture.
• Hands-on experience with LangChain and LangGraph.
• Experience developing AI agents and Agentic AI workflows.
• Good knowledge of embeddings, vector databases, semantic search, and prompt engineering.
• Experience integrating LLMs such as GPT, Claude, Gemini, or equivalent models.
• Strong understanding of API development, backend services, and system integration.
• Good knowledge of SQL and data retrieval techniques.
• Experience with tool calling and external API/service integration.
• Experience deploying and supporting production-grade AI applications.
• Strong problem-solving, analytical, and communication skills.

Preferred Skills

• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with vector databases such as Pinecone, FAISS, Weaviate, Milvus, or Chroma.
• Knowledge of Docker, Kubernetes, CI/CD, and cloud-native deployment.
• Experience with AI evaluation frameworks, observability, and LLM performance optimization.
• Understanding of enterprise security, governance, and responsible AI practices.

Education

Bachelor’s or Master’s degree in Computer Science, Information Technology, Artificial Intelligence, Machine Learning, or a related field.