AI Architect

Experience Required:

• 6 years in Software Engineering with strong exposure to distributed cloud environments (Azure/GCP preferred)

Key Responsibilities:

• Design, build, and scale production-grade agentic orchestration systems managing:
• Multi-agent workflows
• Tool-calling frameworks
• Autonomous decision-making loops at enterprise scale
• Architect and develop a centralized multi-agent platform (hub) to be consumed across cross-functional teams
• Define platform standards, agent registries, and release governance
• Build and optimize RAG (Retrieval-Augmented Generation) pipelines including:
• Semantic retrieval mechanisms
• Grounding strategies
• Robust failure handling across large-scale LLM interactions
• Enable agent-to-agent coordination layers for complex workflows and distributed intelligence
• Work closely with teams to integrate Claude-based coding workflows into development pipelines

Required Technical Skills:

• Hands-on experience with at least one or more frameworks:
• LangGraph
• LangChain
• LlamaIndex
• AutoGen
• CrewAI
• MCP (Model Context Protocol)
• Strong experience building real-world production deployments (not just POCs)
• Deep understanding of:
• Multi-agent architectures
• LLM orchestration
• Tool integrations and API chaining

Cloud & Platform Expertise:

• Proven experience deploying solutions on:
• Azure or Google Cloud Platform (GCP)
• Strong knowledge of:
• Distributed systems design
• Scalable microservices architecture

AI Engineering & Governance:

• Experience implementing:
• Production-grade observability (logging, tracing, monitoring for LLM systems)
• Automated evaluation pipelines for model/agent performance
• PII protection and data governance controls
• Responsible AI guardrails integrated into SDLC

Nice to Have:

• Experience building enterprise AI platforms or internal developer platforms
• Exposure to high-scale LLM workloads (millions of interactions)
• Knowledge of AI safety, compliance, and ethical AI practices