Senior Machine Learning Engineer (Regulatory)

Cboe; Chicago (IL); On-site; USD 150,000 - 210,000; Full time

Job summary

Cboe Global Markets is seeking a Senior Machine Learning Engineer - Regulatory to prototype, train, and deploy ML models and AI applications that monitor financial markets generating terabytes of data daily. You will build and operate production-grade ML infrastructure and data pipelines, with a focus on explainability and governance in a highly regulated environment.

You will work across on-premises and cloud environments, collaborating with companion engineering teams and mentoring junior

Qualifications

• 5+ years of Python development with production practices.
• Experience with enterprise cloud data platforms under RBAC governance.
• Strong SQL and large-scale data handling experience.
• Deep learning with PyTorch and time-series modeling.

Responsibilities

• Prototype, train, and deploy ML models and AI applications for market oversight.
• Develop and operate production-grade ML infrastructure and data pipelines.
• Collaborate with engineering teams across on-premises and cloud environments.
• Produce clear documentation: proposals, experiment specs, designs, and testing scenarios.
• Mentor junior engineers and contribute to code reviews and architecture.

Skills

Python

SQL

Time-series modeling

Deep learning

PyTorch

CI/CD

Docker

Cloud data platforms

RBAC governance

Education

Bachelor's degree in a quantitative field

Tools

Snowflake

Databricks

BigQuery

Job description

• As a Senior Machine Learning Engineer - Regulatory at Cboe Global Markets, you’ll have the opportunity to work with a highly skilled team to prototype, train, and deploy ML models and AI applications that monitor financial markets generating terabytes of new data every trading day
• You’ll be at the forefront of innovation, utilizing advanced AI tools and scalable data engineering to transform complex data into actionable insights
• Collaborate with the team on machine learning experiments across order book analysis, alert detection, and sequential financial data
• Develop and operate AI agent systems in production, applying ML engineering discipline to nondeterministic LLM-based software development workflows
• Own and evolve the team’s ML training and deployment infrastructure on Snowflake
• Build production-quality data pipelines for processing terabytes of daily financial market data
• Raise the engineering bar through rigorous code review, architecture guidance, and mentorship of junior and mid-level engineers
• Design and develop production-quality, test-driven Python code
• Develop explainability and process-compliance solutions for AI and ML
• Effectively track and evaluate ML model performance across training, validation, inference, and monitoring
• Work in both on-premises and cloud environments
• Work closely with complementary engineering teams
• Produce clear and thorough documentation, including ML proposals, experiment specifications, technical design, and testing scenarios
• Communicate technical information clearly and concisely to both technical and end-user audiences
• If you thrive on tackling real-world challenges, excel in programming and large-scale data operations, and want to make a meaningful impact in a fast-paced, highly regulated environment, this is your chance to join a team where your expertise will help shape the future of market oversight. Step into a role where your ideas drive progress, and your contributions truly matter-

Passionate about leveraging cutting-edge Artificial Intelligence and Machine Learning to ensure the integrity and transparency of global financial marketsData-reasoning instinct - able to say what the data is telling you and what data should go into a model in the first place, not just which model to reach forStrong SQL and experience with large-scale datasetsProduction ML experience with time-series / sequential data - you’ve trained, deployed, and monitored models at scale, and you understand how time affects the structure of data: stationarity, regime change, leakage, and why a model that looks good in backtest fails liveDeep learning applied to temporal or representation problems - sequence models, embeddings/similarity over time-series, or equivalentExcellent written and verbal communicationSolid software-engineering foundation: 5+ years, primarily Python, with production practices (version control, automated testing, CI/CD, Docker) and comfort in an enterprise cloud data platform (Snowflake / Databricks / BigQuery, etc.) under real RBAC and governance constraintsBachelor’s degree in a quantitative fieldWe work across deep learning, LLM agent systems, and classical ML. While you don’t need to know all of these, you should have real depth in at least a couple of these, and curiosity about the rest:Deep learning: PyTorch, custom training loops, architecture design and experimentation, multi-GPU distributed ML, experiment tracking, model lifecycle managementLLMs: building with LLM APIs in production, prompt, context, and harness engineering as an engineering discipline, agent orchestration, full stack development using coding agentsClassical ML: scikit-learn, weakly supervised clustering and anomaly detection, feature engineering, model evaluation for production decision systemsTime series and sequential modeling: TCNs, transformers, time-contrastive learning, or similar approaches on temporal data, as well as classical time series modeling (e.g. ARIMA)