Overview
Hybrid
$60 - $70
Contract - W2
Contract - Independent
Contract - 1 Year(s)
Skills
API
Amazon Web Services
Machine Learning (ML)
Jupyter
Pricing
scikit-learn
Research and Development
XGBoost
Job Details
Role: Quantitative Research Engineer
Location: Charlotte, NC Hybrid
- 9+ years in quantitative finance, ML engineering, or similar.
- Build the price engine. Design, train, and deploy time-series and tree-based models (XGBoost, CatBoost, sklearn, lightGBM) that predict fair value and forecast volatility.
- Harden the data layer. Ingest and reconcile auction feeds, marketplace listings, and private-sale data. Handle splits, dupes, zero-comp situations, and stale marks.
- Ship to production. Own model orchestration with Airflow, feature stores, real-time inference endpoints, and rollback strategies.
- Quantitative R&D. Test market microstructure effects (extended bidding, buyer premiums, cash advances) and bake insights into pricing logic.
- API & analytics. Expose Alt Value as a public API, power in-app price alerts, and deliver dashboards the business can act on.
- Python, SQL, AWS (S3, ECS, Lambda), Airflow, dbt, Postgres, Spark, XGBoost, sklearn, CatBoost, GitHub Actions. (Nice-to-have: TypeScript, FastAPI, Grafana, Datadog)
- Deep time-series and forecasting experience, ideally on illiquid or auction assets.
- Proven path from Jupyter to production with CI/CD, testing, and automated monitoring.
- Track record of improving MAE or PnL with your models in live systems.
- Fluent in Python, SQL, and modern data tooling.
- Strong communication: you can explain heteroscedastic noise to engineers.
Employers have access to artificial intelligence language tools (“AI”) that help generate and enhance job descriptions and AI may have been used to create this description. The position description has been reviewed for accuracy and Dice believes it to correctly reflect the job opportunity.