Lead development of an AI-powered analyst agent using LLM integration, tool architectures, and agentic reasoning pipelines. Own Python backend architecture, async workflows, APIs, observability, reliability, and distributed systems. Establish engineering standards, mentor engineers, and partner with product and domain experts to solve complex power-market problems. Design scalable data-rich applications using task queues, SQL and NoSQL databases, and cloud Kubernetes environments.

Conduct research on AI accelerator architectures and semiconductor supply chains to assess power, cooling, and infrastructure implications. Monitor data-center build-outs and industry disclosures, synthesize findings into written briefs and competitive-intelligence products, and ground analysis using Enverus energy datasets.

Lead a small engineering team while remaining hands-on: design and build scalable backend systems and data pipelines on AWS, develop AI/LLM-powered features (RAG, vector stores, agentic workflows), evaluate Gen-AI tooling, drive architecture and technical decisions, enforce best practices, and collaborate cross-functionally to deliver production software with CI/CD.