AI Engineer - NYC

About Sequence If you join Sequence, you'll help build the platform that lets companies get paid - we’re already processing $1bn+ in annual invoice volume and growing fast. We're building the AI-powered revenue platform for modern finance teams, replacing fragile spreadsheets and legacy systems with software their teams love using. Cognition, incident.io, MoonPay, and 100+ other high-growth companies trust us to handle their entire revenue cycle across quoting, billing, and revenue recognition. Founded by repeat entrepreneurs, we hit 10x ARR growth last year and just closed a $20M Series A led by 645 Ventures, alongside a16z and exceptional founders and CFOs from companies like Decagon, Klaviyo and Wise. What's it like to work at Sequence? Small team, big opportunity, real ownership. You'll do work that matters, have direct access to customers, and grow alongside the company. If you want to do the best work of your career at a company that's scaling fast, we'd love to meet you. What you'll be doing We care deeply about the quality of the product we're building. We're looking for engineers who are ambitious and take ownership end-to-end: from identifying what to build, through shipping, to making sure it works for real customers. Here’s what you might work on: Our AI infrastructure. We process over a billion dollars a year through Sequence so correctness is table-stak [... source excerpt omitted ...] flows, prompt iteration, tools, and evals. AI-powered approval workflows. Enterprise deals need approval chains, but rigid workflows break when every company has different rules. You'll build flexible routing that customers configure in natural language - "require VP approval for deals over $100k with annual terms" - and turn that into deterministic, auditable business logic. An intelligent collections agent. Chasing late payments is tedious, manual work. We're building an agent you instruct in natural language (“send a reminder at 7 days overdue; escalate at 14 days”), which then runs the entire workflow and collects the relevant context autonomously. We're a lean team grow [... source excerpt omitted ...] default. See what we’ve shipped in our public changelog. You should apply if You're a builder who wants to solve problems end-to-end: You've shipped LLM-based systems to real customers and have first-hand experience with how they fail in production You've designed agentic systems and have informed views on the building blocks (like embeddings, memory, tool use, long-running state, recovery from partial failures) and when to reach for each You’ve built evals infrastructure (like datasets, LLM as judge, prompt regression tests, monitoring) and have a clear view of what good looks like You respect the weight of building business-critical systems on top of non-deterministic m