We are seeking a Senior Data Scientist to validate, refine, and guide the production deployment of a machine learning model for premium freight pricing. This is a critical, revenue-impacting project where you will work closely with our internal data architect (who has limited ML experience) to transform a learning exercise into a production-grade system. This is a hands-on technical role requiring deep ML expertise, production deployment experience, and the ability to mentor junior team members while delivering results on an accelerated timeline.
Key Responsibilities
- Audit and validate machine learning pricing models, including assessment of training/testing methodology, data leakage risks, and statistical rigor.
- Benchmark model performance against baseline pricing approaches and conduct detailed error analysis to identify weaknesses and failure modes.
- Provide clear recommendations on model readiness, including GO/NO-GO decisions based on performance metrics, robustness, and operational feasibility.
- Collaborate with data engineering and architecture teams to improve models through enhanced feature engineering, data quality improvements, and pipeline design.
- Optimize model performance through hyperparameter tuning, retraining strategies, and techniques to address overfitting, underfitting, and bias.
- Evaluate model improvements using rigorous validation frameworks and holdout datasets.
- Analyze shadow-mode and real-world model performance to identify edge cases, prediction failures, and opportunities for improvement.
- Define production monitoring strategies including performance thresholds, drift detection, retraining triggers, and automated alerting.
- Conduct production readiness reviews and establish guidelines for safe deployment and operational use of models.
- Monitor post-deployment performance, troubleshoot production issues, and ensure model reliability during early rollout phases.
- Document model design, assumptions, limitations, and operational procedures for production environments.
- Provide mentorship and knowledge transfer to internal engineers and data architects on ML best practices, model governance, and MLOps.
- Communicate model insights, technical decisions, and performance implications clearly to both technical teams and business stakeholders.
Qualifications and Technical Skills
- Strong experience developing machine learning models including supervised learning, regression, time-series forecasting, clustering, and optimization techniques.
- Deep understanding of model evaluation, cross-validation, bias-variance tradeoffs, and techniques to prevent overfitting and data leakage.
- Expert-level proficiency in Python and ML ecosystems including scikit-learn, pandas, numpy, TensorFlow, PyTorch, or XGBoost.
- Experience building pricing optimization, demand forecasting, or revenue management models in business environments.
- Strong foundation in statistics, econometrics, and operations research applied to decision-making and optimization problems.
- Experience designing feature engineering pipelines for transactional datasets, particularly logistics data such as shipments, lanes, carrier costs, and demand signals.
- Proficiency in SQL and large-scale data processing frameworks for analytics and feature pipeline development.
- Experience deploying and managing models using cloud ML platforms such as Azure ML, AWS SageMaker, or Google Vertex AI.
- Hands-on experience implementing MLOps practices, including model versioning, retraining pipelines, deployment automation, and monitoring.
- Knowledge of model drift detection, performance monitoring, and automated retraining strategies for production ML systems.
- Experience with controlled experimentation frameworks such as shadow-mode testing or A/B testing to validate model impact.
- Familiarity with modern data platforms such as Snowflake, Databricks, or Apache Spark.
- Strong analytical and problem-solving skills with the ability to translate complex model outputs into actionable business insights.
- Domain knowledge in logistics, freight pricing, supply chain optimization, or transportation analytics is highly desirable.
Minimum Requirements
- Master's or PhD in Computer Science, Statistics, Mathematics, or related quantitative field
- 5+ years of hands-on experience deploying machine learning models to production
- Proven track record of validating and improving existing ML models built by others
- Experience working with revenue-impacting or business-critical ML systems
About SpinTheory
At SpinTheory.ai, we are not just building data platforms; we are engineering the future of how organizations harness data and AI. We aim to transform enterprise complexity into clarity, speed, and measurable business value. As a high-growth startup with global ambitions, we thrive on bold thinking, rapid execution, and relentless curiosity.
We believe in empowering our people as much as our clients. At SpinTheory, you won't just do a job; you will architect the next generation of data and AI ecosystems, working side by side with innovators who challenge the status quo. Flexibility, ownership, and adaptability aren't perks here; they are part of the DNA that fuels our growth.
By joining us, you enter a culture where integrity drives action, customer success defines impact, collaboration sparks innovation, and continuous learning is the only constant. Together, we're creating a future where data and AI don't just inform decisions, they accelerate possibilities.
Core Values: Integrity, Customer Success, Collaboration, Continuous Learning, and Bold Innovation.
