Autonomous AI Agent Developer on Bedrock

Virtusa Corporation; New York (NY); On-site; USD 180,000 - 240,000; Full time

Job summary

Virtusa Corporation seeks an Agentic AI Developer to design, build, and operate autonomous AI agent applications on Amazon Bedrock AgentCore. The role focuses on AgentCore Runtime for scalable agent deployment and on connecting agents to enterprise tools and data via MCP.

You will work across product, data, security, and platform teams to move agentic solutions from prototype to production, implementing observability, security, and robust governance throughout the lifecycle.

Qualifications

• Experience building LLM-based applications or agents using Python or TypeScript.
• Experience with Amazon Bedrock and Bedrock AgentCore (Runtime, Gateway, Memory, or Identity).
• Experience with MCP servers/clients.
• Knowledge of agent design patterns (tool calling, planning, routing, multi-agent orchestration).
• Experience deploying containerized services on AWS (Docker, ECS, EKS, Lambda).
• Familiarity with prompt engineering, RAG, and vector search.
• Ability to communicate technical trade-offs clearly to engineers and non-technical stakeholders.

Responsibilities

• Build agentic applications on AgentCore Runtime with orchestration, tool use, memory, and session management.
• Design and implement MCP servers and clients to expose enterprise tools, APIs, and data sources to agents securely.
• Integrate agents with foundation models through Amazon Bedrock, selecting models and prompting strategies for quality, latency and cost.
• Define agent evaluation approaches, including task success metrics, guardrail checks, and regression testing for non-deterministic behavior.
• Implement observability for agent workflows, covering tracing, logging, token and cost tracking, and failure analysis.
• Apply identity, authentication, and authorization controls to agent actions and tool access with least-privilege principles.
• Collaborate with application, data, security, and DevOps to define requirements, deployment pipelines, and operating procedures.
• Document agent architectures, MCP tool contracts, runbooks, and known limitations for engineering and business stakeholders.

Skills

LLM-based apps

Python

TypeScript

AgentCore Runtime

MCP (Model Context Protocol)

Agent orchestration

Security controls

Observability tracing

Communication of trade-offs

Tools

Docker

ECS

EKS

Lambda

Amazon Bedrock

Bedrock AgentCore Runtime

MCP servers/clients

Vector search

Job description

Virtusa Corporation seeks an Agentic AI Developer to design, build, and operate autonomous AI agent applications on Amazon Bedrock AgentCore. The role focuses on AgentCore Runtime for scalable agent deployment and on connecting agents to enterprise tools and data via MCP.

You will work across product, data, security, and platform teams to move agentic solutions from prototype to production, implementing observability, security, and robust governance throughout the lifecycle.