ML Engineer

Role overview

Own the end-to-end machine learning stack that powers a weekly scan of publicly traded companies, translating thousands of filings, transcripts, and market prints into a short, useful list. The role spans feature engineering over fundamentals and price action through to ranking models and the evaluation harness that an editorial team reviews every cycle. It is a shipping role, where the measure of success is whether next week's brief actually improves.

Responsibilities

- Design and maintain feature pipelines over fundamental data and price action that feed ranking models - Build, train, and iterate on ranking models that surface names doing something genuinely interesting each week - Develop and run the evaluation harness that measures out-of-sample quality and informs editorial review - Take models from raw data through deployment and ongoing monitoring - Partner closely with the research team so that model changes translate into better member-facing output - Defend simple, robust approaches while escalating to more involved architectures when the data justifies it

Requirements

- 5+ years building machine learning systems in production - Strong applied statistics and forecasting background - Demonstrated ownership of a model from data collection through deployment - Prior experience at an early-stage startup - Comfort working remotely as part of a distributed team - Track record of caring deeply enough about a problem to learn its domain-specific quirks

Nice to have

- Familiarity with equity research, fundamentals, or financial datasets - Experience designing evaluation harnesses for non-research stakeholders