Founding Applied AI Engineer

Description

The company is building an Operations Cloud for physical product businesses. It is an AI-native platform that tracks goods, money, and data in real time across procurement, inventory, orders, fulfillment, and finance.

It is meant to replace spreadsheets and rigid ERP systems that depend heavily on consultants. Teams can go live quickly and change their setup as the business changes.

The company's adaptive resource platform and unified operational data model let teams deploy fast, automate workflows, and make changes without lengthy re-implementation.

The company recently closed a $55M Series B led by Madrona and Premji Invest, with participation from Intuit Ventures, Theory Ventures, General Catalyst, Contrary Capital, and Pathlight VC.

This role owns applied AI across the platform. That covers the chat assistant for querying, analyzing, and automating operations, AI-assisted generation of schemas and workflows, and agents that take over routine back-office tasks. You will be the technical lead for connecting foundation models to a transactional system of record, which few ERP products have managed to do well.

Responsibilities

• Own the full applied AI architecture, including model choice, orchestration, RAG over the unified operational data model, evaluations, guardrails, and cost and latency limits in production.
• Turn the chat assistant into the main way operators work, supporting natural-language search, analysis, and automation based on live supply chain, finance, and operations data.
• Build AI tooling that uses foundation models to propose, check, and apply customer schemas and workflow definitions on live production tenants.
• Design agent workflows that stay within enterprise guardrails. They must respect permissions, leave an audit trail, isolate tenants, and be safe to run against a customer's system of record.
• Set up evaluation and observability systems that measure quality, catch regressions, and flag unusual or risky behavior from the system early.
• Work with product, design, and the Forward Deployed team to deliver their most valuable AI use cases.
• Mentor engineers and set the standard for how the team builds, evaluates, and ships LLM-powered systems, acting as the center of applied AI work.

Requirements

• You have shipped LLM-powered features or agents to production and run them at scale, not only prototypes or demos.
• You have hands-on experience with foundation model APIs, RAG pipelines, tool use and function calling, prompt and context engineering, and fine-tuning when it is worth the effort.
• You have built evaluation harnesses and guardrails for non-deterministic systems that work with business-critical data.
• You have strong backend skills, including designing systems, working with Postgres, and using cloud services for reliable multi-tenant web applications.
• You can build from zero in unclear situations, and you know when AI is the right tool and when it is not.
• You are a team player who brings positivity, openness, and curiosity every day.
• You keep learning and look for chances to improve yourself, the team, and the company.
• You care about the quality of what you make.
• You care deeply about the customer's experience and want to build a product that delights them.
• You make pragmatic decisions based on the actual situation rather than theory.
• You work well in collaborative settings and put the team ahead of your ego.