Senior Data Scientist

About Constellation:

Constellation is a cutting-edge AI solution that empowers highly regulated and complex industries with the insights and content they need to fuel their business. Specializing in industries such as healthcare, automotive, insurance, and finance, our powerful data/AI insights tools inform the creation of compliant content at scale. We enable our customers to harness their data and streamline the creation of localized, personalized content. A global, NYC-based company, Constellation has been revolutionizing marketing technology and data intelligence in order to drive exponential growth since its founding in 2016.

Constellation was named the 65th Fastest-Growing Private Company in America, the 10th Fastest-Growing Women-Owned Private Company, and the 7th Fastest-Growing Marketing & Advertising Company by Inc 500. In 2022, our platform won the Digiday Technology Award for Best Marketing Automation Platform.

About the Role

We are seeking an experienced Senior Data Scientist to spearhead the development and optimization of our Automotive predictive models. This role will involve leading end-to-end model development, from data preprocessing to deployment, and collaborating with cross-functional teams to deliver scalable, high-impact AI models and solutions. The ideal candidate is a strategic thinker with deep expertise in machine learning, deep learning, and transformer architectures, self-motivated with a proven ability to drive and advance projects.

What You’ll Do

• Lead Predictive Model Development:
• Model Development: Architect, develop, and fine-tune inventory predictive models to address complex decision-making challenges.
• Model Evaluation: Define and implement metrics to evaluate model performance, iterating on designs to improve accuracy, efficiency, and robustness.
• Model Deployment: Collaborate with engineering teams to deploy models into production environments, ensuring scalability, reliability, and performance.
• Documentation: Document methodologies, experiments, and results.
• Research and Innovation: Stay at the forefront of advancements in deep learning, transformer architectures, reinforcement learning, and sequential decision-making, applying cutting-edge techniques to enhance model performance.
• Mentor & Scale the Team: Coach junior and mid-level data scientists and engineers, review code, drive standards, and help shape a culture of high performance, curiosity, and inclusivity.
• Collaborate Cross-Functionally: Work closely with Product, Engineering, Design, and GTM teams to integrate intelligent systems into customer-facing features and internal tooling.
• Model Business-Critical Outcomes: Develop models for inventory and pricing optimizations, leveraging both structured and unstructured data.
  
  

What We’re Looking For

• Experience:
• 8+ years of experience in data science, ML engineering, or applied AI, with a track record of delivering high performance models (Kaggle competition etc.) and shipping models in production.
• Familiarity with automotive data domains is a strong plus, whether in marketing analytics or vehicle inventory intelligence.
• Technical Expertise:
• Deep experience with Python and classic ML (Pandas, NumPy, Scikit-learn) and modern ML/DL libraries (PyTorch, TensorFlow, Hugging Face).
• Experience leveraging longitudinal data to uncover trends, patterns, and predictive insights for complex, dynamic datasets.
• Preprocessing data skills to prepare both structured and unstructured data for ML/DL models, ensuring data quality, feature engineering, and compatibility with model requirements.
• Deep understanding of transformer architectures, reinforcement learning, and sequential decision-making models.
• Strong command of SQL and data modeling in cloud warehouses (e.g., Snowflake, BigQuery, Redshift).
• Worked with Agile development environment, participating in sprints, stand-ups, and iterative project cycles to deliver high-quality data-driven solutions.
• Develop and maintain production-level code to ensure scalable, efficient, and reliable data pipelines and ML/DL models. 
•  Problem Solving:
• Strong analytical skills with a track record of solving complex, real-world problems using data-driven approaches.
• Mindset to try different approaches and think outside the box.
• Ownership and leadership:
• Proven ability to lead projects, mentor team members, and manage end-to-end model development lifecycles.
• Communication:
• Communication and mentorship skills, with a collaborative mindset and a passion for helping others grow.
  
  

Bonus Experience

• Experience with model lifecycle management, pipelines, monitoring, and experiment tracking using modern tooling like MLflow, SageMaker, or Vertex AI.
• Experience building systems using AWS (Lambda, SageMaker, EC2, Batch, S3) or similar cloud platforms.
• Experience with probabilistic modeling (e.g., PyMC3, Stan).
• Familiarity with graph databases (e.g., Neo4j) and modeling network effects.
• Prior exposure to recommendation engines, survival models, or multi-touch attribution.
• Exposure to Looker, Tableau, or similar BI platforms.

Diversity & Inclusion:

Constellation is an Equal Opportunity Employer,  committed to providing a diverse and inclusive environment.  Here at Constellation we don't discriminate against an applicant or employee on the basis of race, color, religion, creed, national origin, ancestry, sex, gender, age, physical or mental disability, veteran or military status, genetic information, sexual orientation, gender identity, gender expression, marital status, or any other legally-recognized protected basis under federal, state, or local law.

If you need an accommodation during any part of the interview process, due to a disability, please let your dedicated Talent Partner know.

Compensation Package:

The total compensation package is made up of base compensation, equity, and benefits

New York Pay Range: $165,000 - $185,000

#LI-Hybrid: hybrid positions