AI Product Engineer | REMOTE

About the Role

We're looking for an AI Product Engineer to work directly with our CTO to architect and build an agentic harness — a vertical-specific SaaS coworker akin to Claude. This product will bridge tools businesses use to run operations (ERP, CRM, spreadsheets, calendars, email, analytics, compliance systems) and fundamentally change how they interface with their data and systems.

This is not a "bolt AI onto existing features" role. You'll build a new, standalone agentic product from the ground up, acting as both engineer and product owner: scoping problems, making architecture decisions, and shipping with minimal oversight. You'll report directly to the CTO and collaborate with product, engineering, and design teams as this integrates into Distru's broader AI-native roadmap.

Distru is at an inflection point with deep market penetration in cannabis ERP, a growing commerce layer, and an increasingly AI-native roadmap. This role owns one of the most ambitious pieces of that roadmap — building the connective tissue that lets an entire industry run its business through an agentic interface.

Responsibilities

• Build the agentic harness:
  • Architect and build a multi-agent system in production capable of safely operating across core business tools (ERP, CRM, spreadsheets, calendars, email, analytics, compliance systems).
  • Build and maintain MCPs (Model Context Protocol integrations) connecting the harness to real business systems.
  • Own production system concerns end-to-end: reliability, observability, permissions, and safe workflow execution.
• Own the product, not just the code:
  • Define scope, make tradeoff decisions, and drive execution with minimal oversight in an unstructured environment.
  • Design for the user with a product-first mindset, prioritizing usability over technical novelty.
  • Proactively identify and raise risks or open questions, proposing structured solutions.
• Stay at the edge of the AI ecosystem:
  • Keep pace with agent frameworks, harness toolkits, and MCP standards, bringing in better approaches as they emerge.
  • Work hands-on with tools like Claude Code as part of your build process.

Requirements

• 5+ years of full-stack development experience, ideally in B2B SaaS applications.
• Hands-on experience building multi-agent harnesses in production (not just prototypes or personal projects).
• Experience building MCPs (Model Context Protocol) used in production.
• Strong grasp of production system concerns: reliability, observability, permissions, and safe workflow execution.
• Experience operating across product and engineering, comfortable owning scoping and decision-making.
• Proficiency in modern technologies: React, TypeScript, Node, PostgreSQL, GraphQL, and LangGraph, with ability to quickly learn new tools.
• Startup agility: experience at an early-stage startup (under 20 engineers) in ambiguous, unstructured environments.
• Low ego, team-first mentality — success measured by outcomes, not internal politics.
• Clear, proactive communicator who raises concerns and proposes solutions.

Nice-to-Haves

• Background building in supply chain, ERP, CRM, B2B marketplaces, or accounting software.
• Experience with UX design.
• Familiarity with agentic systems and multi-agent orchestration (e.g., evaluation frameworks, agent-to-agent protocols).
• Experience using Claude Code or similar tools to build products independently.
• Cannabis industry experience.

About Distru

Distru is the #1 ERP in the cannabis industry, processing $3B in annual sales through our platform. We're a fully remote, global team building software to streamline the cannabis supply chain. Most top cannabis brands and distributors in the U.S. use our software to manage operations and stay compliant.

We recently launched Distru Commerce, a wholesale platform extending our ERP into the B2B marketplace layer, giving operators a single system for internal operations and external wholesale sales. Our AI Order Agent is live, allowing buyers to submit orders from any source or format, saving time on manual data entry. AI is core to our strategy, aiming to eliminate repetitive work in ERP operations.

We take pride in our culture, reflected in our 5/5 Glassdoor rating. We're stable, profitable, and heavily investing in new product lines. Our investors include Felicis Ventures, Global Founders Capital, Poseidon Asset Management, and Village Global, who have funded companies like Shopify, Cruise, HelloFresh, Facebook, Slack, and Opendoor.

Pay

$120,000 - $200,000 a year. Placement within this range will be determined by the candidate's knowledge, experience, and skills.