Ramp · posted · checked
Research Engineer, Benchmarks & Evaluation
PythonSQL$204k – $352kOn-site · New York and San Francisco
Who can apply
On-site · New York and San Francisco
Location: New York, NY (HQ) / San Francisco, CA
ABOUT RAMP
Ramp is building the smart infrastructure for finance teams, embedded in the transaction flow of every dollar a business spends. We automate how over $275B in annualized spend flows in and out of 85,000+ companies: authorizing payments, flagging risk, categorizing spend, and closing books.
The problems are high-stakes, data-dense, and unforgiving.
We hire people with high agency and high urgency. We look for slope over intercept. We care less about where you trained and more about what you’ve built. At Ramp, everyone is a builder who owns problems end to end and makes consequential decisions that shape the outcome.
The median Ramp customer saves 7.5% and grows revenue 16% in their first year – far in excess of businesses operating without Ramp. We believe every ambitious company deserves the same.
If you want to build systems that directly shape how companies move and manage billions, Ramp is the place to do it.
ABOUT RAMP LABS
Ramp Labs is Ramp's AI research group. We post-train models on finance work, build the environments and evals they learn from, and ship them into the products 70,000+ companies use to move money. We think the defensible part of an AI product is the loop: proprietary environments, evals that track what customers care about, and models trained against both.
ABOUT THE ROLE
Every model decision at Ramp Labs runs through a benchmark. Which model to route to. Whether a post-training run worked. Whether an agent is ready to post a corrective journal entry to a customer's ledger without a human in the loop.
You'll own Ramp's benchmarking effort. You'll turn real finance work (expense policy review, invoice coding, month-end close, spreadsheet Q&A) into benchmarks and RL environments, build the graders, and tell the team what is actually improving.
WHAT YOU’LL DO
Build benchmarks from real workflows: turn agent traces, customer edge cases and expert labels into versioned benchmark suites for long-horizon agents that run for hours across tools and systems, plus tool use, multi-step reasoning and financial judgment
Own the benchmarking effort: decide what we measure, run benchmark suites across models and agent versions, and report results the team makes decisions on