Solution Architect - GenAI

Architect GenAI Solutions: Design end-to-end architectures for AI-powered applications - from LLM selection and prompt engineering through orchestration, retrieval-augmented generation (RAG), and integration with enterprise data environments.

Build and Orchestrate Agents: Go beyond design - build agentic AI workflows using frameworks like LangChain, LangGraph, AutoGen, CrewAI, or similar. You know how to orchestrate multi-agent systems and have shipped something real.

Own the AI Stack: Work across the full GenAI delivery stack: LLM APIs (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock), vector databases, RAG pipelines, evaluation frameworks, and deployment infrastructure.

Bridge to Enterprise Systems: Integrate GenAI solutions with existing enterprise architecture - data platforms, APIs, identity and access controls, and compliance requirements. Make AI work within the constraints of real organizations.

Advise Client Leadership: Translate technical architecture decisions into clear strategic narratives for client leadership. Help clients move from AI experimentation to AI-enabled operations.

Accelerate the Team: Bring patterns, reusable components, and technical standards to the delivery team. Be the person who makes everyone else faster.

Hands-On GenAI Experience: You have built production or near-production GenAI systems - not just demos. You've wrestled with evaluation, hallucination, latency, and cost at the architecture level.

Agentic AI Fluency: Practical experience building agentic workflows and multi-agent systems using frameworks like LangChain, LangGraph, AutoGen, CrewAI, or similar. You understand where these tools shine and where they fall apart.

LLM Platform Breadth: Hands-on experience with major LLM platforms and APIs: OpenAI, Anthropic Claude, Azure OpenAI, AWS Bedrock, or equivalent. You know the trade-offs between them.

Engineering Foundation: Strong Python skills and comfort in cloud-native environments (AWS, Azure, or GCP). You can write the code, not just spec it.

Data Architecture Context: Understanding of how AI systems consume data - vector stores, embeddings, RAG architectures, and the data infrastructure that sits underneath production AI applications.

Consulting & Communication: Experience working in client-facing or consulting delivery contexts. You can navigate organizational complexity and explain AI architecture to both technical teams and senior business stakeholders.

Builder Mentality: You default to building. You use AI tools to accelerate your own work. You're excited to operate at the frontier of what's actually deployable in enterprise environments - not just what's theoretically possible.