Ops / SRE Support Engineer

AI & Solution Architecture 

• Define end-to-end architecture for Generative AI, agentic systems, and AIOps platforms 

• Design scalable, secure, and resilient AI systems across cloud and hybrid environments 

• Establish reference architectures, design patterns, and best practices for AI systems 

Agentic & GenAI Systems 

• Architect multi-agent systems, orchestration workflows, and tool integration frameworks 

• Define patterns for RAG, retrieval pipelines, and knowledge integration 

• Design evaluation frameworks, guardrails, and Responsible AI controls 

• Guide implementation of agent frameworks and workflow orchestration 

• Design patterns for implementation with Agentic Harness 

AIOps & Observability 

• Architect intelligent operations platforms leveraging logs, metrics, traces, and events 

• Define strategies for anomaly detection, alert correlation, and automated remediation 

• Establish observability standards using Open Telemetry (OTEL) and modern monitoring tools like Tempo, Loki, Prometheus, Grafana, etc. 

Cloud & Platform Engineering 

• Lead architecture for AI solutions on Microsoft Azure 

• Design cloud-native systems using containers (Docker, Kubernetes) 

• Define data architecture across PostgreSQL, Cosmos DB, SQL Server, and telemetry pipelines 

Engineering & Delivery Enablement 

• Guide teams on backend architecture using Python and FastAPI 

• Define CI/CD, DevOps, and automation strategies using ADO and GitHub 

• Establish standards for testing, evaluation, and performance optimization of AI systems 

Security, Governance & Responsible AI 

• Define enterprise standards for AI security, privacy, and compliance 

• Implement Responsible AI practices including: 

• Prompt safety 

• Data protection 

• Access control 

• Model governance 

• Ensure auditability and reliability of AI-driven systems 

Operational Excellence 

• Drive improvements in MTTR, MTTD, reliability, and operational efficiency 

• Define SLIs, SLOs, and error budgets for AI-powered services 

• Architect automation for incident response and root-cause analysis 

Leadership & Collaboration 

• Partner with SRE, platform, data, and application teams 

• Mentor engineers and guide architectural decision-making 

• Influence AI strategy and roadmap across the organization 

• Apply strong communication and stakeholder management skills