XOPs Engineer/ ML Ops Engineer

Job Description

Insight Global is seeking an XOPS Engineer for a top enterprise client driving a large-scale AI initiative.

In this role, the engineer will play a huge role in designing, building, and deploying agentic AI proof-of-concepts using AWS Bedrock AgentCore, including the Agent Runtime, Memory, Identity, and Tool Gateway layers. They will work hands-on in Python (3.11+) to develop robust AI services, agent logic, and REST-based microservices that support evolving business use cases. The candidate will write and maintain production-grade Terraform to provision and manage AWS infrastructure such as Bedrock Agents, Knowledge Bases, Lambda, DynamoDB, and IAM, enabling scalable deployments for multiple internal teams. They will partner closely with Marketing and other stakeholders to gather requirements, contribute to solution design, and rapidly iterate on AI initiatives that support large-scale business programs. The role involves building and enabling multi-agent workflows using frameworks like LangGraph, CrewAI, or AutoGen, as well as integrating agents with internal and external systems through Model Context Protocol (MCP) and modern API patterns. The engineer will also create and maintain CI/CD pipelines for automated testing and deployment, implement secure IAM policies following least-privilege principles, support ongoing maintenance and optimization of deployed services, and continuously evaluate emerging AI technologies and AWS capabilities to strengthen the agentic platform.

We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment regardless of their race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances. If you need assistance and/or a reasonable accommodation due to a disability during the application or recruiting process, please send a request to [email protected] learn more about how we collect, keep, and process your private information, please review Insight Global's Workforce Privacy Policy:

Skills and Requirements

• 5-10+ years of experience as an Engineer

• Python(3.11+) hands-on experience building robust applications and agentic logic

• Infrastructure as Code (IaC): Production-level expertise using Terraform to provision AWS services, including Bedrock Agents, Knowledge Bases,DynamoDB, Lambda etc

• CI/CD & DevOps: Proven track record in building and maintaining automated deployment pipelines for cloud-native applications

• AWS Security & Identity: Deep experience with IAM for fine-grained permissions and secure service communication

• AWS Bedrock AgentCore (2025)

? Familiarity with the latest ecosystem, specifically the Agent Runtime, Memory, Identity, and Tool Gateway layer

• Multi-Agent Orchestration

? Experience building or enabling collaborative systems using frameworks like LangGraph, CrewAI, or AutoGen

• Model Context Protocol (MCP)

? Strong understanding of MCP and modern tool/API integration patterns for AI agents

Willingness to learn emerging AI technologies, frameworks, and evolving cloud services