Lead Software Architect I

About the role

You will Set the architecture for model access, retrieval, agent runtime, shared tools, and one place to see traces and scores. Choose when one agent is enough and when work splits across agents. Multi-agent handoff, including A2A, is the agent boundary. Define RAG so index lifecycle, citations, and freshness are part of the design, and judge whether the enterprise data can support it.

What you'll do

• Own the architecture for LLM applications and the platform under them: models, data, agents, evaluations, delivery, and the controls around them
• Set the architecture for model access, retrieval, agent runtime, shared tools, and one place to see traces and scores
• Define RAG so index lifecycle, citations, and freshness are part of the design, and judge whether the enterprise data can support it
• Shape inference for latency and cost: model routing, smaller models where they are enough, caching, and batching where they help
• Write the architecture down and defend the tradeoffs with engineering and with the people who own the business outcome

What you need

• 12–22 yrs of experience
• AWS
• LLMs
• Azure
• GCP
• MLOps
• CI/CD
• Any graduate

Good to have

• Databricks