Lead Software Engineer, AI Platform (Remote)

📋 Description

• • Lead the design, development, and evolution of enterprise-grade AI solutions and MCP servers on AWS, ensuring scalability, security, and alignment with business objectives.
• • Drive adoption of ServiceNow and AWS-native AI capabilities across enterprise platforms to enhance automation and service delivery.
• • Identify and implement AI-driven opportunities that reduce manual effort and improve operational outcomes in key business domains.
• • Design and deliver a repeatable, domain-aligned software template using Spotify Backstage to standardize AI service integration across teams.
• • Architect production-ready MCP servers with integrated authentication, role-based access control (RBAC), and secure communication protocols.
• • Develop reference Python-based MCP servers tailored for enterprise systems such as Workday, ensuring compatibility and reliability.
• • Implement shared authentication libraries supporting Entra ID and OAuth 2.0/OIDC flows, including On-Behalf-Of token exchanges and JWT validation.
• • Build a tool-accuracy evaluation harness to validate LLM tool behavior within CI pipelines, ensuring consistent performance and safety.
• • Automate registration of AI agents with AWS Bedrock AgentCore Gateway to enable seamless integration with enterprise AI workflows.
• • Manage containerized deployments on AWS ECS Fargate using read-only filesystems to enforce security and immutability standards.
• • Deploy and maintain infrastructure-as-code using Terraform or CloudFormation to provision and manage AWS resources consistently.
• • Instrument comprehensive observability across services using OpenTelemetry tracing and structured JSON logging for real-time monitoring and debugging.
• • Conduct regular technical design reviews and architecture governance sessions to uphold platform integrity and best practices.
• • Transfer knowledge to the platform team through live demonstrations, documented runbooks, and architectural guidelines to enable team scalability.
• • Collaborate with cross-functional stakeholders to align AI infrastructure initiatives with enterprise-wide integration goals and compliance requirements.
• • Ensure all systems adhere to AWS security best practices, including IAM role chaining, Secrets Manager usage, and VPC network hardening.
• • Maintain high standards of technical documentation for architecture decisions, deployment procedures, and operational runbooks.
• • Support hybrid and remote work models while ensuring seamless collaboration and delivery across distributed teams.
• • Participate in on-call rotations and incident response for critical AI infrastructure components as needed.
• • Promote a culture of continuous improvement through code reviews, pair programming, and innovation in AI platform tooling.
• • Uphold Lennar’s commitment to quality, compliance, and operational excellence in all software development and deployment activities.