Demo
Careers

Machine Learning Engineer, Signal

EngineeringFull-timeNew York or Remote

What we do

The events that move markets and the data that trains models both happen in the real world first - long before they show up in a packaged vendor dataset. EdgeOrigin closes that gap: our edge nodes listen to real-world events where they occur and deliver evaluated records with the provenance a research desk or a training pipeline can trust.

Our customers are hedge funds that trade on our signal and AI teams that train on our data. The technical work spans global event listening, low-latency evaluation, point-in-time history, and regional delivery, with production responsibility from ingestion through client delivery.

About this role

As an ML Engineer on the Signal team, you'll own the models that separate signal from noise - the ones that read the raw global stream and judge urgency, authenticity, and data quality before a record ever reaches a customer.

You'll own that work from the first question to production: framing the real problem, working through messy real-world data, prototyping approaches, and validating them until the output is something a trading desk or a training pipeline can trust. The models run on live data at scale, so they have to be both accurate and fast.

What you'll do

  • Own the urgency, quality, and extraction models end to end, from data and training through evaluation and production.
  • Turn noisy, multi-source raw data into clean, structured, evaluated signal.
  • Build the evaluations that keep quality honest as sources and conditions change.
  • Make the models fast enough to run inline on a real-time stream.
  • Partner with data engineering so your models plug cleanly into the pipeline.
  • Keep models healthy in production - watch for drift, catch regressions, ship changes safely.

What we're looking for

  • 5+ years building and shipping ML systems in production, with real ownership of models that served live traffic.
  • Strong applied background in NLP, information extraction, time-series, or ranking at scale.
  • Expert in Python and the modern ML stack (PyTorch, Hugging Face, scikit-learn), with the ability to work beyond framework abstractions.
  • Experience serving models at low latency and the discipline to measure what you ship.
  • Comfortable with large-scale data tooling (Spark, Ray, Kafka) to drive training and inference.
  • Comfortable owning open-ended production problems on a small team with broad technical scope.

Nice to have

  • Experience with financial or alternative data, or with satellite / remote-sensing extraction.
  • Background in anomaly detection, event detection, or forecasting.
  • Familiarity with vector search and retrieval over large corpora.

This role is for you if you are

  • Turns messy real-world data into measurable, reliable model behavior.
  • Can move from an ambiguous signal question to a measurable evaluation and reliable production behavior.
  • Works effectively on a small team where technical judgment, direct collaboration, and production ownership matter.

Apply

Apply for Machine Learning Engineer, Signal

Links

Resume

A few more details

In your own words

Voluntary self-identification

EdgeOrigin is an equal-opportunity employer. Completing the fields below is entirely voluntary and is kept separate from the hiring decision - it will not help or hurt your application in any way.

Not quite your role? Browse all open roles or introduce yourself.

EdgeOrigin is proud to be an equal-opportunity employer. We celebrate difference and are committed to building an inclusive team where everyone can do their best work, regardless of race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, or any other characteristic protected by law. If you need a reasonable accommodation at any point in the process, tell us at [email protected] and we'll make it happen.

By submitting an application, you agree to EdgeOrigin's Terms of Service and Privacy Policy.