ML Quant Developer / ML Engineer

TL;DR

ML Quant Developer / ML Engineer (Machine Learning/Quantitative Research): Developing machine learning models, predictive features, and production data pipelines for quantitative trading with an accent on time series, alternative data, and rigorous statistical validation. Focus on testing market inefficiency hypotheses, preventing data leakage in backtests, and integrating model predictions into trading strategies.

Location: Not specified

Company

Advantage Solutions combines quantitative research and machine learning to develop data-driven trading strategies.

What you will do

• Formulate and test hypotheses about market inefficiencies using rigorous backtesting.
• Determine how model predictions can support directional bets, spread convergence, and other trading approaches.
• Design predictive features using statistical transformations and learned representations.
• Analyze alternative data, time series, and nonlinear dependencies to identify trading signals.
• Build reliable production data pipelines beyond notebook-based experimentation.

Requirements

• 4+ years of production machine learning experience.
• Deep understanding of machine learning methods, including gradient boosting, neural networks, and Bayesian and frequentist approaches.
• Hands-on experience with deep learning and gradient boosting frameworks, plus a strong understanding of neural network internals.
• Strong knowledge of statistics, probability theory, and stochastic processes, with careful attention to assumptions and failure modes.
• Solid Python skills; experience with pandas, polars, or streaming data processing is beneficial.
• Professional English proficiency at B2 level or above is required.

Nice to have

• Graduate of SHAD or a comparable top-tier technical or quantitative program.
• Background in competitive mathematics, physics, or computer science olympiads.
• Strong results in Kaggle or other machine learning competitions.

Culture & Benefits

• No finance experience is required; training covers market microstructure and portfolio construction.
• Emphasis on clear reasoning, asking useful questions of data, and maintaining research integrity.