AI product engineer

Distru provides an ERP and B2B eCommerce platform for the cannabis industry, supporting inventory, manufacturing, sales, and logistics. It is building AI infrastructure and an agentic ecosystem for commercial businesses.

• Architect and build a production multi-agent system that safely takes actions across Distru and customers’ core systems
• Iterate on and maintain the MCP connecting Distru to Claude and Codex
• Own reliability, observability, and durable execution end to end
• Write evals to improve agentic systems using real customer use cases
• Build a unified data system that consolidates data from multiple sources into a layer exposed to Claude and Codex via an MCP
• Build a contextual memory system that ingests customer data and improves agent performance
• Set architectural standards for building, testing, and shipping agents, and bring the engineering team along
• Track agentic frameworks, harnesses, toolkits, and models, and introduce better approaches
• Rapidly prototype ideas for the team and customers
• Build hands-on with Claude Code and similar tools
• Improve the agentic coding workflow and share discoveries with the team
• Talk directly with customers and the GTM team

• 7+ Years in full-stack development, ideally on B2B SaaS applications
• Hands-on experience building multi-agent harnesses in production, not just prototypes or personal projects
• Experience building MCPs used in production
• Strong understanding of reliability, observability, permissions, and safe workflow execution
• Experience operating across product and engineering, including owning scoping and decisions
• Proficiency in React, TypeScript, Node, PostgreSQL, GraphQL, and LangGraph; ability to learn new tools and frameworks quickly
• Experience at an early-stage startup with fewer than 20 engineers, setting direction amid ambiguity
• Team-first approach and focus on shipped outcomes rather than internal politics
• Experience shaping the roadmap, not just executing it
• Ability to raise concerns and propose solutions proactively
• Daily use of AI tools and ability to explain areas of strength and ongoing development in AI fluency
• Будет плюсом: experience building supply chain, ERP, CRM, B2B marketplace, or accounting software; UX design experience; agentic systems work beyond the must-haves, such as evaluation frameworks or agent-to-agent protocols; experience using Claude Code or similar to build products independently; cannabis industry experience

• Fully remote across 4 continents
• Employee-friendly option terms: after 2 years, a 10-year window to exercise if you leave
• 18 Days PTO + 11 holidays; sick days don't count toward PTO
• Medical, dental, vision + 401(k) for US employees
• Access to best-in-class AI tools and a generous AI stipend for everything else
• Yearly in-person team offsites
• Benefits vary by country and employment type
• The interview process includes three short written application questions in Lever about building with LLMs; a 30-minute recruiter screen; a 45–60-minute technical interview; a 3–4-hour harness take-home; a 60-minute take-home review; references and offer