> Markdown version of [/jobs/ext/1916010-senior-data-scientist-detection-modeling](https://www.wearedevelopers.com/jobs/ext/1916010-senior-data-scientist-detection-modeling). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior Data Scientist - Detection & Modeling

- **Company:** TWG, INC.
- **Location:** Santa Monica, CA, United States
- **Experience:** Expert
- **Salary:** $190,000.0 - $290,000.0
- **Contract:** Permanent contract
- **Skills:** Machine Learning, Feature Engineering
- **Published:** August 4, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=8051566dce86057d

## About the Role

* Strong feature engineering and applied ML on transactional or time-series data
 * Hands-on experience with anomaly detection and unsupervised methods (e.g., isolation forests, density-based methods, autoencoders)
 * Solid statistical foundations, including model calibration and working with imperfect labels
 * Production ML experience - you ship, monitor, and maintain models over time
 * Comfort scaling a modeling approach across many detectors, market types, and venues, rather than building one-off models
 * Fraud, risk, integrity, or market-surveillance domain experience a plus FIX / market-microstructure fluency a plus; on-chain data familiarity a plus

## Description

As a Senior Data Scientist for Detection & Modeling, you'll own the features and models at the core of the surveillance systems - the layer that turns raw trading behavior into scored, explainable signals - and you'll evolve that layer as the systems mature and the labeled datasets grow. The work now spans two detection stacks on different grains: the account-grain L1-L3 stack on the US exchange and the wallet/cluster-grain D1-D3 stack of the DeFi Integrity Engine. The two seats split by venue focus while operating as one modeling practice: shared methodology (robust statistics on heavy-tailed data, calibration discipline, the labeling loop), different substrates. This is a hands-on modeling role with a lot of room to shape the detection architecture over the life of the program., * Design and refine features on large-scale financial time-series and on-chain data, with an emphasis on signals that hold up under noisy, heavy-tailed conditions

 * Develop and improve anomaly-detection models across both supervised and unsupervised approaches
 * Evolve the model architectures as labels accumulate - from simpler classifiers toward multi-class, per-scenario, and ensemble designs; on the DeFi side, activate the supervised layer from a standing start as the first disposition labels arrive
 * Improve detector calibration so scores are trustworthy and comparable across market types and venues
 * Partner with the validation and analyst teams on the labeling pipelines that supply the models' training signal


## Related Videos

- [Introduction to Azure Machine Learning](https://www.wearedevelopers.com/videos/368-introduction-to-azure-machine-learning)
- [Anomaly Detection - Using unsupervised Machine Learning for detecting anomalies in customer base](https://www.wearedevelopers.com/videos/6-anomaly-detection-using-unsupervised-machine-learning-for-detecting-anomalies-in-customer-base)
- [What is relational learning and why does it matter?](https://www.wearedevelopers.com/videos/396-what-is-relational-learning-and-why-does-it-matter)
- [What non-automotive Machine Learning projects can learn from automotive Machine Learning projects](https://www.wearedevelopers.com/videos/397-what-non-automotive-machine-learning-projects-can-learn-from-automotive-machine-learning-projects)
- [How computers learn to see – Applying AI to industry](https://www.wearedevelopers.com/videos/756-how-computers-learn-to-see-applying-ai-to-industry)
- [Detecting Money Laundering with AI](https://www.wearedevelopers.com/videos/111-detecting-money-laundering-with-ai)

## Related Articles

- [How machine learning can help us tell fact from fiction](https://www.wearedevelopers.com/magazine/509-how-machine-learning-can-help-us-tell-fact-from-fiction)
- [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production)
- [Trustworthy AI Starts at Deployment: 5 Checks Before You Ship](https://www.wearedevelopers.com/magazine/753-trustworthy-ai-starts-at-deployment-5-checks-before-you-ship)
- [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models)
- [Dev Digest 134 - Where pixels sing?](https://www.wearedevelopers.com/magazine/477-dev-digest-134-where-pixels-sing)
- [MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production](https://www.wearedevelopers.com/magazine/115-mlops-deploying-maintaining-and-evolving-machine-learning-models-in-production)