Experience:

• 3–5+ years of software engineering experience
• 1+ years building and observing AI/ML or GenAI applications preferred

Qualification:

• Bachelor’s in Computer Science, AI/ML, Data Science, or a related field

Responsibilities:

• Build agent runtime management capabilities including agent registry, versioning, deployment tracking, and run histories
• Enable operational workflows such as incident triage, replay/debug runs, trace correlation, and root-cause analysis
• Implement operational dashboards for agent health metrics like success rate, latency, tool failure rate, cost per run, and loop detection
• Instrument agent flows end-to-end using OpenTelemetry or equivalent
• Implement semantic conventions and tagging standards
• Partner with SRE/observability teams for production-grade monitoring, alerting, and operational readiness
• Collaborate with transformation teams and business stakeholders to tailor AI agents to specific domains
• Work closely with AI platform teams to build scalable and cross-domain AI agents with end-to-end observability
• Build and maintain CI/CD pipelines for agent services and operations center components
• Automate onboarding for new agent use cases
• Drive best practices for secure, scalable, and cost-effective agent deployments
• Stay updated with AI and machine learning advancements and integrate them into AI agents
• Conduct testing and validation to ensure reliability and accuracy of AI agents

Nice to have:

• Experience building internal developer platforms or operational consoles
• Strong engineering discipline including testing, versioning, CI/CD, and automation
• Operational mindset focused on reliability, debuggability, and incident response support
• Problem-solving skills to translate business challenges into technical solutions
• Collaboration skills for effective cross-functional teamwork
• Agility to adapt to changing requirements and new technologies
• Communication skills to explain complex technical concepts to non-technical stakeholders

More skills:

agentic frameworks (Crew.ai, LangChain, Semantic Kernel, AutoGen, or similar), microservices patterns, RAG patterns (embeddings, vector search, retrieval evaluation, chunking strategies), cloud environments (Azure, AWS, GCP), containerized deployments (Kubernetes, AKS, EKS), observability fundamentals (logs, metrics, traces), distributed tracing, telemetry pipelines, Azure AI Search, prompt/version management, evaluation frameworks, Responsible AI practices (data handling, safety guardrails, audit trails, redaction strategies), FinOps (token/GPU cost optimization, chargeback/showback reporting)