AI Engineer – Agentic AI & Multi-Agent Systems | AWS Bedrock, LangChain & LangGraph

Overview

Design, develop and deploy enterprise-grade AI agents and multi-agent systems using modern agentic AI frameworks, covering the full lifecycle from solution design through production deployment.

What you'll do

• Design and develop autonomous AI agents and multi-agent workflows that address defined business and operational needs.
• Build agentic applications using Amazon Bedrock, AgentCore, LangChain, LangGraph, Strands Agents SDK, and related frameworks.
• Implement orchestration, planning, memory management, tool calling, routing, and human-in-the-loop capabilities.
• Design, develop, and integrate solutions based on the Model Context Protocol.
• Create scalable agent architectures that follow established AI agent design patterns and engineering best practices.
• Translate product and business requirements into clear technical designs, implementation plans, and measurable outcomes.
• Collaborate with product managers, software engineers, data specialists, security stakeholders, and other delivery teams.
• Evaluate and optimize LLM performance, response quality, reliability, latency, cost, and safety.
• Develop reusable components, documentation, testing approaches, and operational procedures for AI agent solutions.
• Support production deployment, troubleshooting, monitoring, and continuous improvement of AI applications.
• Apply responsible AI, privacy, security, and sustainability considerations throughout the solution lifecycle.

What you'll need

• Strong hands-on Python development experience for AI applications, APIs, automation, and production services.
• Hands-on experience designing and implementing generative AI and agent-based solutions with Amazon Bedrock.
• Hands-on experience using AgentCore for AI agent development, orchestration, or deployment.
• Expertise in building LLM-powered applications, tool integrations, chains, and agent workflows with LangChain.
• Expertise in designing stateful, controllable, and multi-step agent workflows with LangGraph.
• Practical experience developing agentic applications with Strands Agents SDK or a similar agent framework.
• Experience designing or integrating Model Context Protocol (MCP) based solutions.
• Strong understanding of prompt engineering, tool calling, planning, memory, routing, and workflow coordination.
• Experience implementing multi-agent systems in which multiple specialized agents collaborate to complete tasks.
• Deep understanding of AI agent design patterns for planning, reflection, delegation, routing, supervision, memory, and human-in-the-loop controls.
• More than 6 years of professional experience in software engineering, AI engineering, data engineering, or closely related roles.
• At least 2 years of hands-on experience developing AI, generative AI, LLM, agentic AI, or related solutions.
• Practical experience designing and implementing AI agents, agent workflows, tool calling, memory management, LLM orchestration, and multi-agent systems.
• Bachelor's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related field; equivalent relevant experience or demonstrated technical capability may be considered.
• Ability to write maintainable, testable, and production-ready code.
• Understanding of data handling, access control, retention, and traceability for LLM applications and AI agents.
• Understanding of cloud-based deployment considerations for AI agents, including scalability, availability, access management, and operational support.
• Experience with the software development lifecycle, including requirements analysis, design, development, testing, deployment, and support.
• Ability to create technical documentation, solution designs, test plans, and operational runbooks.
• Experience validating agent behavior through functional, integration, regression, and quality testing.
• Ability to use measurable criteria to evaluate response quality, reliability, latency, cost, and safety.
• Understanding of secure prompt, tool, data, and API integration practices, including access controls, input and output validation, and protection of sensitive information.
• Awareness of risks associated with prompt injection, unauthorized tool use, data leakage, unsafe outputs, and excessive agent autonomy.
• Ability to incorporate responsible AI, privacy, reliability, and safety controls into agent solutions.

Nice to have

• Experience deploying cloud-native AI applications in AWS environments.
• Exposure to frameworks and components used to build Retrieval-Augmented Generation (RAG) based applications.
• Familiarity with monitoring, tracing, evaluation, quality measurement, and performance analysis for AI agents.
• Experience with software components and practices used to deploy, operate, and maintain generative AI applications.
• Experience with additional programming languages used in cloud-native or enterprise application development.
• Experience with asynchronous programming and event-driven application development.
• Exposure to vector databases or vector search technologies for RAG applications.
• Experience designing retrieval, indexing, metadata, and document-processing workflows.
• Familiarity with data stores used for conversation history, agent state, or long-term memory.
• Experience with cloud-native deployments on AWS.
• Familiarity with containerized services, serverless components, event-driven architectures, and infrastructure automation.
• Understanding of cloud cost management and resource optimization for AI workloads.
• Experience with CI/CD, version control, automated testing, containerization, and infrastructure-as-code practices.
• Familiarity with agile delivery methods and iterative product development.
• Experience establishing observability and operational metrics for AI agents.
• Experience implementing security controls in AWS-based applications.
• Familiarity with auditability, identity and access management, secrets management, encryption, and security monitoring.
• Experience defining human approval or escalation controls for higher-risk agent actions.
• Experience delivering enterprise-grade, cloud-based, regulated, or operationally critical software solutions.
• Relevant cloud, AI, generative AI, software engineering, or professional technology certifications.

Details

• Location: Bengaluru - Bellandur (GTP).