Among computer and information research scientists, AI is already used for a large share of the tasks. Measured exposure for computer and information research scientists: 34% (high).

Share of this job’s tasks that AI is already used for at work, from real usage. It is not a forecast of job loss, and a low number means no use seen yet. Source: Anthropic Economic Index.

Check how this applies to your own job

Skills this job asks for

Say which you have and which you want to build. We use it to match you to jobs like this one.

About the job

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

We are looking for a Staff Engineer with experience building Agentic AI systems to help design and ship production multi-agent systems at the core of LeanData's new platform of autonomous agents for go-to-market teams.

This is a Staff-level individual-contributor role with founding-level ownership. You would work closely with engineering and product leadership to define and build the architecture of a sophisticated multi-agent system able to reason over go-to-market data and act reliably at enterprise scale. This a Senior technical position — any engineer can tell a coding agent to build things; we are looking for people who know how to design and deliver production agentic systems that actually work safely when connected to customers' live data systems, and who give deep thought to best-practices for building production agentic systems. We know just about every candidate for this position has built agentic systems — we are going to ask how you made sure the systems you built work.

This role reports to the Director of Engineering - AI and Machine Learning, and is based in our Santa Clara, CA office. You are required to be in office Mondays and Wednesdays each week.

What you'll be doing

Designing and building multi-agent systems that are able to work with complex, dirty data structures and varying policies to safely write to mission-critical customer data stores

Establish patterns and best practices that help the whole team build better and faster

Agent control loops and planning, the orchestration graphs and tools they call, and the coordination, handoffs, state, and durability across agents

Build the safe write-back path that applies agent decisions to a customer's live systems without corrupting data

Measure, test, and evaluate everything you ship: build the eval cases, rubrics, and regression tests that prove a change made the agent better

Guardrails for agentic systems

Integrate frontier LLMs behind a model-agnostic abstraction with routing by task, cost, and latency; own the cost, latency, and reliability of your surface, and create the patterns that let the team build agents faster

Requirements

4+ years building production systems, including 2+ years shipping LLM-powered or agentic systems

You have shipped customer-facing LLM or agent systems that real users depend on, and can explain how they failed and how you fixed them

High agency: you scope, prioritize, and ship without waiting for permission

Ability to reason, make decisions, and act in the face of ambiguity

Strong, current Python (TypeScript or Go a plus)

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), plus skill debugging deep, non-deterministic failures in multi-step agent traces

Bonus points if you have

Experience with Salesforce APIs (Bulk 2.0, Composite, Pub/Sub) or another large, messy enterprise data source

A founder or founding-engineer background, or contributions to open-source agent or LLM tooling

Compensation

The salary for this role will be between $160,000 and $200,000 base, plus equity.