
IN-Manager_ Senior AI Engineer/Architect – GenAI Solutions _IN IT Services CO_IFS_PAN India
- Bangalore, Karnataka
- Permanent
- Full-time
- Design, develop and deploy LLM-powered intelligent agents and RAG-based applications using frameworks like LangChain, LangFlow, and LangGraph.
- Implement LangFuse for observability, latency tracking, and hallucination detection in GenAI pipelines.
- Build scalable semantic search pipelines using vector databases such as Qdrant, Pinecone, Azure AI Search, and integrate with LLM-driven workflows.
- Develop Python-based microservices for embedding AI capabilities into enterprise-grade platforms using frameworks such as FastAPI, FastMCP, Flask, or Django.
- Leverage OpenAI, Gemini, Claude, or open-source LLMs (e.g., LLaMA, PaLM, Mistral) via APIs or self-hosted models for multi-turn conversations and knowledge-driven tasks.
- Construct multi-hop reasoning, tool-calling agents capable of real-world decision-making across domains like customer support, marketing, and operations.
- Automate deployment of AI solutions, using Azure DevOps or GitHub Enterprise and GitHub Actions.
- Effectively collaborate with data engineers, AI developers and product teams to review existing AI Solutions architecture and identify technical alternatives to improve non-functional capabilities of existing solutions.
- Align GenAI solutions with business use cases and ensure robust delivery pipelines.
- Define and implement in-house evaluation metrics for latency, grounding, factual consistency, and user engagement.
- Proficiency in Python with a strong understanding of data structures, concurrency, and REST API development and deployments on Serverless environments on Microsoft Azure.
- Extensive, hands-on experience with GenAI tools: Predominantly,
- LangChain (Agents, Chains, Callbacks, Tools),
- LangFlow (Visual orchestration of agent workflows),
- LangGraph (Stateful graph-based agent routing),
- LangFuse (Monitoring & Evaluation).
- Proven experience with RAG-based system design, including chunking, embedding generation, retrieval strategies (dense, hybrid), and feedback loops.
- Exposure to Azure AI Services like AI Search (formerly Cognitive Search), Document Intelligence.
- Exposure to Microservices-oriented and Containerized deployment architecture leveraging Azure Kubernetes Services (AKS)
- Hands-on with Vector Stores: Qdrant, Azure AI Search, Pinecone, Chroma, Weaviate.
- Solid understanding of Embedding Models, Chat
- Extensive experience building and deploying LLM solutions in cloud environments like Azure.
- Exposure to observability tooling and latency optimization strategies in GenAI pipelines.
- Experience in prompt engineering, context synthesis, and few-shot learning patterns.
- Working knowledge of CI/CD pipelines to deploy AI solutions, using Azure DevOps or GitHub Enterprise and GitHub Actions.