AI Engineer – Agentic AI | Bedrock, LangChain & LangGraph

Overview

Design and deliver enterprise-grade AI agents and multi-agent systems using Amazon Bedrock, AgentCore, LangChain, LangGraph, MCP and agent design patterns, covering architecture, implementation, orchestration, evaluation, deployment and ongoing improvement.

What you'll do

• Design and develop autonomous AI agents and multi-agent workflows.
• Build agentic applications using Amazon Bedrock, AgentCore, LangChain, LangGraph, and Strands Agents SDK.
• Implement orchestration, planning, memory management, and tool-calling capabilities.
• Design and integrate Model Context Protocol-based solutions.
• Create scalable agent architectures following industry best practices and AI agent design patterns.
• Collaborate with product and engineering teams to translate business requirements into AI-driven solutions.
• Evaluate and optimize LLM performance, reliability, safety, latency, and operational efficiency.
• Develop reusable agent components, tools, prompts, workflows, and integration patterns.
• Define and apply testing and evaluation approaches for agent behavior and LLM responses.
• Support the deployment, monitoring, troubleshooting, and continuous improvement of AI applications.
• Apply security, privacy, responsible AI, and sustainability considerations throughout the solution lifecycle.
• Document architecture, implementation decisions, evaluation results, operational procedures, and known limitations.

What you'll need

• Strong professional Python development experience for building AI applications, services, integrations, and automation.
• Hands-on experience developing generative AI and agentic AI solutions with Amazon Bedrock.
• Hands-on experience using AgentCore for AI agent development, orchestration, or deployment.
• Expertise in building LLM-powered applications, chains, tools, and agent workflows with LangChain.
• Expertise in developing stateful, controlled, and multi-step agent workflows with LangGraph.
• Practical experience building agentic applications with Strands Agents SDK or similar agent frameworks.
• Knowledge and implementation experience with MCP-based solutions.
• Deep understanding of AI agent design patterns: planning, routing, delegation, reflection, memory, supervision, tool use, and human-in-the-loop controls.
• Experience implementing multi-agent systems in which multiple specialized agents collaborate to complete tasks.
• Strong understanding of prompt design, agent coordination, tool calling, planning, memory management, and workflow execution.
• Ability to write maintainable, modular, testable, production-ready code, and to develop APIs, agent tools, integrations, and AI application services.
• Understanding of error handling, logging, testing, and performance considerations in Python applications.
• Understanding of data management for LLM applications and AI agents, including data quality, access control, retention, traceability, and responsible data usage.
• Understanding of cloud-based deployment considerations for AI agents, including scalability, availability, access management, and operational support.
• Experience across the software development lifecycle, including requirements analysis, design, development, testing, deployment, and support.
• Ability to create technical designs, implementation plans, test cases, evaluation reports, and operational documentation.
• Experience testing agent workflows, tool integrations, LLM responses, and multi-agent behavior.
• Ability to assess and improve response quality, reliability, safety, latency, and cost.
• Familiarity with version control and collaborative software development practices.
• Understanding of secure prompt, tool, API, and data integration practices, including input and output validation, access controls, and protection of sensitive information.
• Awareness of risks related to prompt injection, unauthorized tool use, data leakage, unsafe outputs, and excessive agent autonomy.
• More than 6 years of professional experience in software engineering, AI engineering, data engineering, or a related technical role.
• At least 2 years of hands-on experience in AI, generative AI, LLM, agentic AI, or related solution development.
• Practical experience designing and implementing autonomous AI agents and multi-agent workflows.
• Bachelor's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related discipline; equivalent relevant experience or demonstrated technical capability may be considered.

Nice to have

• Experience deploying AI solutions in cloud-native AWS environments.
• Exposure to Retrieval-Augmented Generation (RAG) architectures and related implementation approaches.
• Familiarity with AI observability, evaluation, and monitoring tools for agent quality, reliability, performance, and operational behavior.
• Knowledge of productionizing, operating, and maintaining GenAI applications.
• Experience with asynchronous programming and event-driven application development.
• Exposure to vector databases and vector search technologies.
• Experience with CI/CD pipelines, automated testing, containerization, and infrastructure-as-code practices.
• Experience implementing security controls in AWS-based applications.
• Experience defining human approval, escalation, or review controls for higher-risk agent actions.
• Relevant certifications in cloud technologies, AI, generative AI, or software engineering.

Details

• Location: Bengaluru - Bellandur (GTP).