Associate Process Manager

Location:- Mumbai/Pune

Experience:- 6-10 years

Key Responsibilities

• Design, develop, and deploy Agentic AI systems leveraging Large Language Models (LLMs) to enable autonomous reasoning, task orchestration, and intelligent decision-making.
• Build multi-agent architectures capable of planning, tool usage, and workflow automation for complex enterprise workflows.
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines integrating vector databases and enterprise knowledge sources.
• Implement advanced prompt engineering, context management, guardrails, and evaluation frameworks to improve response accuracy, reliability, and reduce hallucinations.
• Integrate LLM-based agents with external APIs, internal microservices, and enterprise systems to enable intelligent tool-driven workflows.
• Architect and implement scalable AI-powered applications using AWS serverless services including Lambda, API Gateway, Step Functions, EventBridge, DynamoDB, and S3.
• Design event-driven and microservices-based architectures for AI workloads ensuring scalability, fault tolerance, and low latency.
• Deploy and manage AI services using AWS Bedrock, SageMaker, containerized workloads on ECS/EKS, and third-party LLM APIs.
• Collaborate with product, data science, and engineering teams to translate business requirements into scalable AI-driven solutions.
• Continuously evaluate and adopt emerging Generative AI, agent frameworks, and cloud technologies to enhance system capabilities.

Required Skills

• Strong experience building applications using Generative AI and Large Language Models (LLMs).
• Hands-on experience designing agentic workflows, autonomous agents, and multi-agent orchestration systems.
• Experience with modern AI frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, or similar agent frameworks.
• Strong understanding and implementation experience with Retrieval-Augmented Generation (RAG) architectures.
• Familiarity with vector databases and embeddings such as Pinecone, OpenSearch, or FAISS.
• Strong programming expertise in Python for AI/ML systems and backend services.
• Hands-on experience with AWS cloud-native architectures, particularly:
  • AWS Lambda
  • API Gateway
  • Step Functions
  • EventBridge
  • DynamoDB
  • S3
• Experience deploying and managing containerized applications using Amazon ECS and Amazon EKS.
• Experience working with AWS Bedrock, SageMaker, or external LLM APIs.
• Understanding of distributed systems, microservices architecture, and event-driven architectures.
• Experience integrating LLM agents with APIs, enterprise tools, and data platforms.