Description

Key Responsibilities

Agentic AI Solution Development · Design and develop sophisticated multi-agent AI systems for enterprise use cases. · Build autonomous and semi-autonomous AI workflows using Agentic AI patterns. · Implement supervisor-worker, sequential, orchestration, choreography, ReAct, Planner-Executor, and Writer-Critic agent architectures. · Develop scalable agent communication and execution frameworks. · Design closed-loop AI workflows with validation, retry, evaluation, and feedback mechanisms. Enterprise AI Platform Engineering · Build reusable AI platform capabilities consumed by multiple business teams. · Implement enterprise-grade AI governance and operational controls. · Design API-driven AI service architecture with: o Rate limiting o Quota management o Multi-tenant usage tracking o Cost attribution o Authentication & authorization o Audit logging · Enable structured onboarding and lifecycle management of AI agents. Multi-Agent Orchestration · Design orchestration frameworks where agents communicate through: o Direct calls o Event-driven architectures o Message queues o Publish-subscribe patterns · Implement choreography and conductor-based execution models. · Evaluate technologies such as Kafka, Azure Durable Functions, Service Bus, and event-driven workflows. AI Memory & Knowledge Systems · Design short-term and long-term memory architectures. · Implement: o Vector databases o Semantic caching o Conversation memory o Agent state persistence o Retrieval-Augmented Generation (RAG) · Develop knowledge orchestration frameworks supporting agent collaboration. Ontology & Graph-based Intelligence · Work with graph databases and enterprise knowledge models. · Support ontology-driven AI applications. · Build knowledge graphs that enable relationship-based reasoning and signal generation. · Design systems that combine structured, unstructured, and graph-based knowledge sources. Model Governance & FinOps · Implement AI consumption governance across business domains. · Track: o Token usage o Model consumption o API utilization o Operational costs · Create chargeback/showback mechanisms for enterprise teams. · Support AI FinOps reporting and capacity planning. Reliability, Monitoring & Observability · Design observability frameworks for AI applications. · Monitor: o Agent executions o Tool usage o Latency o Hallucinations o Failure rates o Model quality · Create dashboards and operational metrics for enterprise AI workloads. Responsible AI & Security · Implement: o Guardrails o Safety controls o Prompt protection o Data masking o PII protection o Human-in-the-loop validation · Ensure compliance with enterprise security and governance policies. · Build secure agentic systems handling sensitive business data. AI Evaluation & Optimization · Develop frameworks for: o Agent evaluation o Tool evaluation o Response quality measurement o Closed-loop evaluation o Hallucination detection · Apply advanced AI engineering techniques including: o Context engineering o Prompt engineering o Retrieval optimization o Agent tuning o AI system benchmarking Required Qualifications Experience · 7+ years in software engineering or platform engineering. · 3+ years building AI/ML or Generative AI solutions. · Experience delivering enterprise-scale production AI applications. · Experience designing AI architectures rather than only building individual AI applications. Technical Skills Generative AI & Agentic Frameworks · Azure AI Foundry · Azure OpenAI · LangChain · LangGraph · Semantic Kernel (preferred) · MCP (Model Context Protocol) Cloud Platforms · Microsoft Azure (required) · Experience with GCP or AWS is a plus Enterprise Integration · API gateways and AI governance platforms · Azure API Management (APIM) · REST APIs · Event-driven systems Programming · Python (required) · C# (.NET) preferred · SQL Data & Storage · Cosmos DB · PostgreSQL · MongoDB · Vector databases · Graph databases (Neo4j, Stardog, Neptune, etc.) Messaging & Streaming · Kafka · Azure Service Bus · Event Grid · Durable Functions AI Operations · AI observability · Monitoring & logging · Token usage analysis · Cost optimization · Model lifecycle management Preferred Qualifications · Experience implementing ontology-driven solutions. · Experience with enterprise knowledge graphs. · Experience building autonomous AI systems. · Experience with AI governance and responsible AI frameworks. · Experience designing reusable AI platforms used by multiple business units. · Experience with healthcare, financial services, insurance, or regulated industries. What Success Looks Like Within the first 6-12 months, this role will: · Deliver scalable multi-agent AI solutions for enterprise use cases. · Establish reusable AI platform capabilities across multiple business domains. · Implement AI governance, monitoring, and cost attribution frameworks. · Build enterprise-grade orchestration patterns and memory architectures. · Improve AI system reliability, observability, and operational maturity. · Enable business teams to rapidly develop AI-powered applications on a secure, governed platform. My assessment based on the transcript The interviewer was effectively looking for someone who can discuss: · Architecture trade-offs · Agent orchestration patterns · Choreography vs orchestration · Memory management strategies · Graph databases & ontology · AI platform governance · APIM and AI gateway patterns · Closed-loop evaluation · Harm/Risk/Context engineering · Cost attribution and multi-tenant AI platforms
 

Key Skills

Education

Bachelor's degree