Staff Engineer, Agentic AI

The role

You will design and ship production multi-agent systems for a new platform of autonomous agents. You will work with engineering and product leadership to build architecture that reasons over go-to-market data at enterprise scale.

What you will do

• Designing and building multi-agent systems that work with complex data structures and varying policies
• Establish patterns and best practices to help the team build better and faster
• Work on agent control loops, planning, orchestration graphs, tools, coordination, handoffs, state, and durability
• Build the safe write-back path for agent decisions to customer live systems
• Measure, test, and evaluate everything shipped using eval cases, rubrics, and regression tests
• Develop guardrails for agentic systems
• Integrate frontier LLMs behind a model-agnostic abstraction
• Own the cost, latency, and reliability of the surface

Required qualifications

• 4+ years building production systems
• 2+ years shipping LLM-powered or agentic systems
• Shipped customer-facing LLM or agent systems that real users depend on
• High agency: scope, prioritize, and ship without waiting for permission
• Ability to reason, make decisions, and act in the face of ambiguity
• Strong, current Python
• Hands-on with a modern agent framework / orchestration (e.g. LangGraph or agent SDKs), tool/function-calling, structured outputs, retrieval (RAG), and context/memory management
• Strong systems-engineering fundamentals (concurrency, distributed systems, statefulness, latency and cost at scale)
• Skill debugging deep, non-deterministic failures in multi-step agent traces

Nice to have

• TypeScript or Go
• Experience with Salesforce APIs (Bulk 2.0, Composite, Pub/Sub) or another large, messy enterprise data source
• A founder or founding-engineer background
• Contributions to open-source agent or LLM tooling

About the company

LeanData helps the world's fastest-growing companies automate, simplify, and accelerate revenue.