Key Responsibilities
AI-Augmented Software Development
Integrate LLMs into IDEs and CI/CD pipelines for:
Code generation (Type Script, Golang, Python)
API scaffolding (REST, Graph QL)
Unit, integration, and security test creation
Code refactoring and documentation
Build AI agents to recommend best practices, detect security flaws, and align with compliance standards (TISAX, SOC, Fed RAMP, AWS Gov Cloud).
AI-Driven Testing & Quality Engineering
Automate test case generation for APIs, microservices, and infrastructure.
Use AI to generate test data, assess test coverage, and recommend improvements.
Implement AI-based load testing pattern generation and test output analysis.
Infrastructure & Dev Ops Intelligence
Architect AI-enhanced CI/CD pipelines (Argo CD, Jenkins, Tekton) with predictive deployment analysis and rollback automation.
Use AI to:
Parameterize and refactor Terraform modules
Translate Terraform to Cloud Formation
Align infrastructure with AWS WAR, NIST, and Prisma Cloud recommendations
Enable self-healing infrastructure and cost optimization recommendations.
Observability & SRE Automation
Build AI agents to:
Analyze Istio, Prometheus, and logging data
Detect anomalies and correlate events
Recommend or auto-apply fixes
Monitor pipelines and infrastructure for performance, cost, and reliability insights.
Security & Compliance Automation
Integrate AI tools for CVE detection, patch generation, and Ia C hygiene.
Translate compliance requirements into policy-as-code using NLP.
Align infrastructure with AWS Gov Cloud and single-account models.
Documentation & Knowledge Management
Use AI to generate and improve:
Architecture and design docs from code
Microservice documentation for reuse and onboarding
Release notes, training labs, and customer-facing documentation
Cross-Functional Collaboration
Partner with engineering, QA, SRE, and documentation teams to align AI initiatives.
Collaborate with other BUs to adopt or extend shared LLMs and AI tools.
Lead POCs, benchmarks, and production rollouts of AI-driven workflows.
Qualifications
Must-Have
7+ years in cloud architecture, Dev Ops, or full-stack engineering
2+ years applying AI/ML in software engineering workflows
Deep experience with:
AWS, GCP, Azure
Terraform, Helm, Kubernetes
CI/CD (Argo CD, Jenkins, Tekton)
Observability (Prometheus, Open Telemetry, ELK)
Full-stack development (Node.js, Python, React/Vue)
Proven ability to integrate or build AI-enhanced developer tools
Nice-to-Have
Experience with MLOps platforms (MLflow, Sage Maker, Kubeflow)
Familiarity with AI security tooling and compliance automation
Certifications: AWS/GCP Architect, CKA, etc.