Senior Data Scientist - Validation & Information-Driven Trading

TWG Global AI•New York, NY

1d•$190,000 - $290,000•Onsite

About The Position

At TWG AI, we drive innovation and business transformation across a range of industries—including financial services, insurance, technology, media, and sports—by leveraging data and AI as core assets. Our AI-first, cloud-native approach delivers real-time intelligence and interactive business applications, empowering informed decision-making for both customers and employees. We prioritize responsible data and AI practices, ensuring ethical standards and regulatory compliance. Our decentralized structure enables each business unit to operate autonomously, supported by a central AI Solutions Group, while strategic partnerships with leading data and AI vendors fuel game-changing efforts in marketing, operations, and product development. You will collaborate with management to advance our data and analytics transformation, enhance productivity, and enable agile, data-driven decisions. By leveraging relationships with top tech startups and universities, you will help create competitive advantages and drive enterprise innovation. At TWG, your contributions will support our goal of sustained growth and superior returns, as we deliver rare value and impact across our businesses.

Requirements

Strong empirical and statistical background: hypothesis testing, permutation / resampling methods, backtesting, and careful inference
Experience working with weak, noisy, or evolving labels and human-in-the-loop labeling systems
Production ML experience and the discipline that comes with regulated, audit-facing work

Nice To Haves

A quantitative finance or empirical-research background (including relevant PhD or equivalent industry experience) a strong plus
Sequential-modeling experience; transformers or RNNs applied to behavioral or transaction sequences is a plus

Responsibilities

Build detection logic for insider and information-driven trading, centered on the timing of when information became public versus when it was acted on — on both venues, with the identity boundary each venue supports
Design and run rigorous validation of the systems' outputs — statistical testing, permutation-based informativeness testing against market-resolution ground truth, backtesting against known cases — to demonstrate the detectors work
Own the quality and trustworthiness of the labels that train the models, treating labeling as a continuously improving process rather than a fixed dataset — including the DeFi label corpus, which the program creates from zero
Grow the validation work into a repeatable, audit-ready assurance capability as the systems expand to new markets
Mentor more junior team members contributing to the validation and analysis work