Founding Engineer

Burnt’s building an agentic OS for the Food Supply Chain with AI Agents for each department. Our first AI Agent replaces the whole order management team at food distribution companies that sell into restaurants.

Our agent monitors all incoming messages, figures out if it's an order, learns each customer's habits, shorthand, and favorite products, picks up on any prep notes, and enters it straight into the existing ERP. The more it sees, the smarter it gets.

Help Build the Future of Autonomous Supply Chain Management

At Burnt, we’re building an AI-native operating system for the food supply chain—replacing legacy ERPs with intelligent agents that automate 80% of the work across sales, operations, credit control, and even ERP implementation. Distributors today are drowning in fragmented data, buried in email and WhatsApp orders, and losing millions to bad debt, frozen inventory, and failed SAP projects. Our agents automate order capture, follow up on overdue invoices, resolve SKU mismatches, and can even compress ERP go-lives from 2 years to 2 months. One of the hardest technical challenges we’re solving is the lack of unified context—food distributors' data is spread across disconnected systems, APIs, PDFs, and spreadsheets. We're building a "truth store" for each enterprise and a swarm of memory-augmented agents to act on it. As a founding engineer, you’ll work across LLM orchestration, retrieval-augmented generation, multi-agent planning, and real-time decision systems—powering the backend of a vertically integrated AI company that deeply understands supply chain workflows. Our stack includes Python, Java (Spring Boot), AWS (Lambda, Step Functions, RDS), Pinecone, and foundation models from OpenAI and Bedrock. If you’re excited to own architectural decisions, ship real-world AI products, and build systems that can change how the $10T+ supply chain industry operates, we’d love to talk.

At Burnt, we’re building an Agentic operating system for the food supply chain, replacing slow, error-prone ERP workflows with intelligent agents across sales, operations, credit control, and implementation. Distributors today wrestle with outdated systems, manual order entry from emails and WhatsApp, credit teams buried in follow-ups, and inventory locked up due to disconnected processes—resulting in lost revenue and rising operational costs. Even worse, traditional ERP implementations take 12–18 months and often fail. We're building implementation agents that reduce go-live time to weeks by auto-mapping SKUs, learning from customer data, and adapting to edge cases through feedback loops. Technically, this means tackling messy, unstructured inputs, real-time decisioning, multi-tenant architecture, and long-term memory across agents. Our stack includes Java (Spring Boot), Python, AWS , Pinecone for semantic search, and LLMs from OpenAI and Bedrock. If you’re excited by vertical SaaS, applied AI, and building intelligent systems that do real work, we’d love to talk.

1. Initial conversation with CEO (30 mins)
2. Tech interview with CTO
3. Cultural round with CPO (30min)
4. In-office white boarding session (3 hours)
5. Final team conversation (45 mins)