Applied AI Engineer

Sapien is rethinking how finance teams operate in the age of AI. We’re building toward an autonomous CFO—systems that run company financials end-to-end. Our platform analyzes complex financial data in real time to increase decision cadence, prevent costly mistakes, and surface value. Sapien has caught multi-million-dollar errors, saved thousands of jobs, and returned significant dollars to customers’ bottom lines.

We partner with traditional businesses—manufacturing, healthcare, restaurants, and large enterprises—to deeply understand and automate their financial workflows. We’re HQ’d by Madison Square Park in NYC and backed by General Catalyst, Neo, and top operators from Google, OpenAI, Microsoft, Ramp, and Stripe (over $9M raised).

You'll build the AI agent capabilities that power Sapien's autonomous finance operations. This means designing novel architectures for reasoning over complex financial data, implementing verifiable and observable agent workflows, and building systems that learn and adapt to each company's unique operations.

This is a research-meets-product role. You'll work on cutting-edge agent capabilities—from observability and library learning to semantic search and multi-modal parsing—and ship them directly into production for customers.

• Design and implement agent architectures that enable observability, human-in-the-loop verification, and precise context control across complex financial workflows.

• Build library learning systems that reduce LLM dependencies by learning reusable patterns for planning, code generation, and data localization from customer interactions.

• Create graph-based company representations and develop efficient search methods using embeddings, semantic clustering, and custom retrieval strategies.

• Build multi-modal parsers that unify diverse financial data sources (Excel, ERPs, CRMs) into coherent, queryable schemas that agents can reason over.

• Implement RL and fine-tuning pipelines based on user feedback, pairwise preferences, and implicit interaction signals to improve agent performance over time.

• Design benchmarking and evaluation suites that quantify Sapien's accuracy, reliability, and business impact across different customer workflows.

• Quality experience building production AI/ML systems—deploying models at scale, ideally in complex, data-intensive domains.

• Strong algorithmic thinking. Demonstrated through ML research, competitive programming, mathematics, or building novel systems from scratch.

• Deep experience with modern agent frameworks, LLMs, and AI systems: fine-tuning, retrieval augmentation, tool use, or agentic architectures.

• Comfort working end-to-end: from implementing research ideas and prototyping architectures to deploying production systems and iterating on real customer feedback.

• Ability to move between abstraction levels—designing high-level agent workflows while debugging low-level implementation details.

• CS, Math, or Engineering degree or equivalent experience. We care most about what you've built.

• Adaptability: You thrive on diverse, open-ended problems. One day you're implementing a new agent architecture, the next you're debugging a customer data issue—and you bring the same intensity to both.

• Ownership: You take problems from research paper to production. You don't wait for direction—you identify what needs to happen and drive it to completion.

• Opinionated: You have strong technical perspectives on what works and what doesn't. You push back on approaches you disagree with and make the team's thinking sharper.

• Mission-driven: You're energized by building AI that transforms how businesses run. You connect technical decisions to real customer outcomes and care deeply about the impact.

• Collaborative excellence: You share knowledge, give thoughtful feedback, and invest in making the team better. You bring new ideas from papers and discussions to elevate everyone's thinking.