Software Engineer, AI

Software Engineer, AI Ambrook helps American family-run businesses become more profitable and resilient. From volatile markets to climate shifts, independent operators face mounting pressure. While sustainable investments often yield the best long-term returns, they require financial clarity and capital that fragmented legacy systems can’t provide. We are rebuilding the financial infrastructure that independent operators rely on. By replacing paperwork with modern tools for accounting, banking, and spending, Ambrook gives owners the data they need to prove viability to lenders and the next generation. We empower the stewards of land and labor to make confident investments in their future. We’re a Series A startup backed by Thrive Capital, Dylan Field, and Homebrew. We’re looking for early team members to help us untangle the intersection of American industry, climate, and the economy. The opportunity Ambrook is building a world-class team to empower farmers, ranchers, and small-business owners using modern AI tools. You’ll shape how we use LLMs and intelligent systems to make messy, high-stakes financial workflows faster, smarter, and more accessible for users across the country. We’re shipping features across the financial landscape, from better receipt parsing and review to auto-categorization to intelligent conversational AI features that let people get a deeper understanding of their books and their business with fewer clicks. We’ve got a big vision of making AI work for real family businesses, not just mega-corps. If you’re interested in building with us, let’s talk. We’re looking for someone who we can count on to… - Own: Development of intelligent systems and tools that use LLMs, NLP, and heuristics to streamline bookkeeping, inbox triage, and financial workflows. - Teach: Best practices around ML system design, evaluation, prompt engineering, and scalable AI infrastructure. - Learn: How messy real world financial data really is - from scanned PDFs to unformatted CSVs to text-heavy emails - and how to make sense of it using language models. - Improve: Our internal tooling and infrastructure for classification, tagging, summarization, and user-in-the-loop AI systems. Within 1 month you'll... - Build and ship a feature powered by an LLM - e.g., parsing a new type of paper document, or categorizing financial transactions. - Review our current uses of AI and write up a note identifying where AI could meaningfully improve automation and accuracy. - Collaborate with product and engineering to understand customer workflows and where AI would reduce manual pain. Within 3 months you'll... - Establish early foundations for evaluation pipelines, prompt management, and feedback loops to improve LLM performance over time. - Implement or improve systems for document extraction and financial transaction tagging, using both heuristics and model-based approaches. - Collaborate closely with design and product to make AI features feel reliable, intuitive, and helpful, not mysterious or brittle. Within 6 months you'll... - Architect and scale systems for automated bookkeeping and analysis using hybrid AI + rule-based systems. - Contribute to our long-term AI strategy: which tasks to automate, how to measure confidence, and when to keep a human in the loop. - Help build internal tooling for prompt iteration, embedding search, labeling, and retraining. - Share learnings in a post on Ambrook Research or an open-source tool that helps others tackle similar messy real-world data problems. About you - You've built and shipped ML/AI-driven features, ideally with LLMs, in a product that’s in production, not just in a notebook. - You're excited to apply language models to real-world, unstructured, often ugly datasets, and turn them into valuable product experiences. - You're pragmatic about AI: you know when to use an LLM, when to write a regular expression, and when to ask the user. - Bonus: Experience working with LL ... (truncated, view full listing at source)