Senior Specialist - Data Sciences

AI Engineer – Agentic AI & Advanced RAG

Exp- 8-12 Years

AI Application Development

• Design, develop, and deploy GenAI and Agentic AI solutions using modern LLM frameworks and tools.
• Build intelligent AI agents capable of reasoning, planning, tool execution, and workflow automation.
• Develop scalable backend services and APIs for AI applications using Python and FastAPI.
• Translate business requirements into robust AI-powered solutions.

Agentic AI Development

• Develop and maintain AI agents using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or Google ADK.
• Implement agent workflows involving task decomposition, memory management, reasoning, and tool integration.
• Build and support multi-agent collaboration patterns and orchestration workflows.
• Integrate external tools, APIs, databases, and enterprise applications into agent ecosystems.

Advanced RAG Implementation

• Design and implement Retrieval-Augmented Generation (RAG) pipelines to improve AI response quality and accuracy.
• Build document ingestion, chunking, embedding generation, retrieval, and response synthesis workflows.
• Implement advanced retrieval techniques including hybrid search, semantic search, metadata filtering, and agentic retrieval.
• Integrate enterprise knowledge repositories and structured/unstructured data sources into AI applications.

Knowledge & Data Engineering

• Develop and maintain vector database and semantic search solutions using Pinecone, FAISS, ChromaDB, or other vector stores.
• Work with Knowledge Graphs and metadata-driven architectures to enhance contextual reasoning.
• Implement memory and context management strategies for AI agents.

AI Evaluation & Observability

• Develop automated evaluation frameworks for AI applications.
• Measure performance using metrics such as answer relevance, faithfulness, hallucination detection, latency, and user satisfaction.
• Utilize tools such as RAGAS, DeepEval, LangSmith, Langfuse, and Arize AI.
• Monitor production AI systems and proactively identify quality, reliability, and performance issues.

Engineering Excellence

• Write clean, scalable, and production-ready code following engineering best practices.
• Participate in code reviews, architecture discussions, and design workshops.
• Support CI/CD implementation and deployment automation for AI solutions.
• Troubleshoot and optimize AI applications for performance, scalability, and reliability.

We are seeking a highly skilled AI Engineer with expertise in Generative AI, Agentic AI, and Advanced RAG architectures. The ideal candidate will be responsible for developing enterprise-grade AI applications, intelligent AI agents, and scalable AI platforms that leverage Large Language Models (LLMs), knowledge systems, and agent orchestration frameworks. You will work closely with business and technology teams to build innovative AI-powered solutions that drive automation, productivity, and business value.

AI Application Development

• Design, develop, and deploy GenAI and Agentic AI solutions using modern LLM frameworks and tools.
• Build intelligent AI agents capable of reasoning, planning, tool execution, and workflow automation.
• Develop scalable backend services and APIs for AI applications using Python and FastAPI.
• Translate business requirements into robust AI-powered solutions.

Agentic AI Development

• Develop and maintain AI agents using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or Google ADK.
• Implement agent workflows involving task decomposition, memory management, reasoning, and tool integration.
• Build and support multi-agent collaboration patterns and orchestration workflows.
• Integrate external tools, APIs, databases, and enterprise applications into agent ecosystems.

Advanced RAG Implementation

• Design and implement Retrieval-Augmented Generation (RAG) pipelines to improve AI response quality and accuracy.
• Build document ingestion, chunking, embedding generation, retrieval, and response synthesis workflows.
• Implement advanced retrieval techniques including hybrid search, semantic search, metadata filtering, and agentic retrieval.
• Integrate enterprise knowledge repositories and structured/unstructured data sources into AI applications.

Knowledge & Data Engineering

• Develop and maintain vector database and semantic search solutions using Pinecone, FAISS, ChromaDB, or other vector stores.
• Work with Knowledge Graphs and metadata-driven architectures to enhance contextual reasoning.
• Implement memory and context management strategies for AI agents.

AI Evaluation & Observability

• Develop automated evaluation frameworks for AI applications.
• Measure performance using metrics such as answer relevance, faithfulness, hallucination detection, latency, and user satisfaction.
• Utilize tools such as RAGAS, DeepEval, LangSmith, Langfuse, and Arize AI.
• Monitor production AI systems and proactively identify quality, reliability, and performance issues.

Engineering Excellence

• Write clean, scalable, and production-ready code following engineering best practices.
• Participate in code reviews, architecture discussions, and design workshops.
• Support CI/CD implementation and deployment automation for AI solutions.
• Troubleshoot and optimize AI applications for performance, scalability, and reliability.

Programming & Development

• Strong hands-on development experience in Python.
• Experience developing REST APIs and microservices using FastAPI.
• Strong understanding of software engineering best practices, testing frameworks, and API development.

Agent Frameworks

• Hands-on experience in one or more of the following:
  • LangChain
  • LangGraph
  • AutoGen
  • CrewAI
  • Google ADK
• Experience building AI agents and agentic workflows.

Generative AI & RAG

• Strong experience implementing Advanced RAG solutions.
• Understanding of embeddings, semantic search, vector retrieval, re-ranking, hybrid search, and prompt engineering.
• Experience integrating enterprise knowledge sources into GenAI applications.

Multi-Agent Systems

• Knowledge of multi-agent architectures and agent orchestration patterns.
• Experience implementing tool calling, workflow automation, and agent collaboration mechanisms.

Vector Databases

• Experience with one or more vector databases:
  • Pinecone
  • FAISS
  • ChromaDB
  • Weaviate
  • Milvus

AI Evaluation & Observability

• Hands-on experience with:
  • RAGAS
  • DeepEval
  • LangSmith
  • Langfuse
  • Arize AI
• Understanding of evaluation methodologies for LLM and RAG applications.

Emerging AI Technologies

• Knowledge of:
  • MCP (Model Context Protocol)
  • Knowledge Graphs
  • Agent Memory Patterns
  • Function Calling and Tool Integration