Gen AI Architect

We are looking for a GenAI Architect to lead the enterprise-scale architecture of our Agentic AI platform. This role blends distributed systems, applied AI, and platform engineering to deliver secure, scalable, production-grade GenAI solutions.

The ideal candidate is tool-agnostic and architecture-focused, with the ability to combine Microsoft’s AI ecosystem with best-in-class open-source frameworks.

What You Will Do

Agentic System Architecture

• Architect and implement multi-agent systems using frameworks such as Semantic Kernel, Microsoft Agent Framework, LangGraph, CrewAI, or AutoGen
• Design hybrid orchestration combining agentic reasoning and deterministic workflows
• Implement agent-to-agent communication and Model Context Protocol for tool discovery and invocation

Retrieval, Reasoning, and Knowledge Systems

• Build enterprise-grade RAG and Agentic-RAG pipelines using Azure AI Search or open-source vector platforms such as LlamaIndex, Haystack, Milvus, Weaviate, or Qdrant
• Enable multi-hop reasoning across structured and unstructured data
• Integrate with Microsoft Fabric, Dataverse, Cosmos DB, and enterprise data lakes

AI Governance, Safety, and Observability

• Design governance layers for prompt filtering, PII protection, content moderation, and policy enforcement
• Implement observability for prompts, agent actions, cost, latency, and risk
• Use tools such as Microsoft Purview, AI Content Safety, Guardrails AI, NeMo Guardrails, Arize Phoenix, LangSmith, MLflow, or OpenTelemetry

LLMOps and Model Infrastructure

• Own the full LLM lifecycle including prompt flows, routing, evaluation, versioning, and deployment
• Work with Azure OpenAI and open-source models such as Llama, Mistral, and Qwen
• Build CI/CD pipelines using GitHub Actions, Azure DevOps, MLflow, BentoML, or similar
• Design scalable inference on Kubernetes and cloud using vLLM, TGI, KubeRay, SkyPilot, or managed services

Backend and Integration

• Build AI control planes in Python (FastAPI, asyncio, Pydantic) and/or C# (.NET)
• Implement tool-calling APIs, workflows, agent memory, and enterprise system integrations

Human-in-the-Loop Interfaces

• Build real-time AI interfaces using React and TypeScript
• Enable streaming responses via WebSockets or Server-Sent Events
• Create dashboards for approval, override, and guidance of agent actions
• Integrate solutions into Microsoft Teams, web portals, developer tools, and VS Code AI Toolkit

What You Bring

Core Engineering

• 8+ years in backend, platform, or distributed systems
• Strong expertise in Python and/or C#
• Experience building APIs, microservices, and event-driven systems

GenAI and Agent Systems

• 3+ years building production-grade GenAI solutions
• Experience with agent frameworks, RAG, tool-calling, and agent memory

Data and Search

• Experience with Azure AI Search or vector databases
• Strong understanding of embeddings, hybrid search, and retrieval pipelines

AI Safety and Observability

• Experience implementing guardrails, policy engines, and LLM monitoring
• Tracing, evaluation, and telemetry for AI systems

LLMOps and Infrastructure

• CI/CD for AI workloads
• Model experimentation and tracking
• Azure, Docker, Kubernetes, Terraform or Pulumi

What We Offer

At Delphi, we provide a supportive, growth-focused environment. You will receive competitive compensation, performance-based incentives, and comprehensive health benefits. We invest in your growth through company-sponsored certifications, training programs, and continuous learning opportunities.

We promote an inclusive and flexible culture with remote work options, fully supported work-from-home setups, wellness programs, and a strong focus on mental well-being.