Senior Machine Learning Engineer

**Job Title**: Senior Machine Learning Engineer **Reports to**: Lead Machine Learning Engineer Intelligent Audit is a fast\-growing freight audit \& business analytics technology company helping our customers become smarter shippers \- shipping to their customers faster, cheaper, and with less delivery exceptions. We use big data to help our customers remove inefficiencies in their global transportation spend. As a **Senior Machine Learning Engineer** within the Data Science organization, you will design, build, and maintain production\-grade ML solutions on large logistics, shipping, and billing datasets. You will own models and services end\-to\-end (exploration and prototyping through deployment, monitoring, and continuous improvement), while collaborating closely with data science, product, engineering, and operations teams. **What You Will Do:** *Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions. The individual with this position in our company will be expected, on a regular basis, to:* * **ML design and development** Architect, implement, and maintain ML models (e.g., gradient boosted trees, deep learning, forecasting, transformers) using Python and its data science ecosystem (NumPy, pandas, polars, Scikit\-learn, PyTorch, XGBoost, Jupyter, visualization libraries). * **Data analysis and feature engineering** Explore, visualize, and analyze large internal and external datasets, especially structured multivariate time\-series, logistics, and billing data, to engineer features, validate assumptions, and improve model performance. * **Production systems and APIs** Develop robust, well\-structured code and internal APIs (e.g., FastAPI) for online and batch inference, integrating ML services into existing systems and workflows. * **Code quality and engineering practices** Apply software engineering best practices including version control, code reviews, documentation, and test\-driven development to ensure clarity, reliability, and maintainability. * **MLOps, CI/CD, and observability** Design and operate CI/CD pipelines (e.g., GitHub Actions) for ML workloads; build and maintain containerized deployments (Docker, Kubernetes or similar); instrument experiment tracking and monitoring using tools such as MLflow, TensorBoard, Datadog, Neptune, or Weights \& Biases. * **Data engineering collaboration** Work with relational and analytical data stores (Postgres, parquet, DuckDB) and collaborate with data engineering on SQL\- and dbt\-based pipelines that support training, validation, and production scoring. * **LLM integration** Use LLM APIs and tools (e.g., OpenAI, Cursor) and prompting strategies to integrate LLMs into products, workflows, and data pipelines where they provide clear business value. * **Lifecycle ownership and continuous improvement** Own the ML lifecycle: problem framing, data exploration, modeling, evaluation, deployment, monitoring, retraining, and decommissioning; identify opportunities to reduce technical debt and improve performance and reliability. * **Collaboration, communication, and mentorship** Translate complex ML and statistical concepts into clear language for technical and non\-technical stakeholders; document and present findings and design decisions; provide guidance and feedback to junior data scientists and engineers. **What You Will Bring:** * Strong analytical and problem\-solving skills with a focus on machine learning and data\-driven decision making. * Advanced Python proficiency and deep familiarity with data science libraries and tooling (NumPy, pandas, polars, Scikit\-learn, PyTorch, XGBoost, Jupyter). * Experience with deep learning and decision tree–based methods, including production use of models such as gradient boosted trees and neural networks. * Proven experience working with structured multivariate time\-series and other large structured datasets. * Proficiency with Linux, Git, Bash, and working in cloud or remote high\-performance computing environments for big data and large\-scale training. * Hands\-on experience with CI/CD pipelines, containerization (Docker), and orchestration (Kubernetes or similar) for ML workloads. * Experience with monitoring, logging, and experiment tracking for ML systems (e.g., MLflow, TensorBoard, Datadog, Neptune, Weights \& Biases). * Comfort working with SQL and relational databases (Postgres) as well as analytical formats and engines (parquet, DuckDB), and collaborating with data engineering on dbt or similar tooling. * Experience with LLM APIs, integration patterns, and prompting strategies for LLM\-powered workflows and applications. * Strong written and verbal communication skills and a track record of successful collaboration with cross\-functional stakeholders. * Interest in mentoring and helping level up team members on ML, MLOps, and software engineering best practices. **Minimum Qualifications** * Bachelor’s, Master’s, or Ph.D. in Computer Science, Data Science, Mathematics, Physics, Statistics, or a related quantitative field, **or** equivalent practical experience demonstrating senior\-level ML engineering capability. * At least 5 years of professional Python development experience focused on data science and ML libraries. * At least 3 years of experience delivering end\-to\-end ML solutions in production (from exploration through deployment and monitoring). * At least 3 years of experience with deep learning and decision tree–based methods. * At least 2 years of experience working with structured multivariate time\-series data. * Demonstrated experience with: + CI/CD pipeline design and operation for ML workloads. + Containerization (Docker) and orchestration (Kubernetes or similar). + Linux\-based cloud and/or remote high\-performance computing environments. **Preferred Characteristics:** * Ph.D. or equivalent research experience focusing on cutting\-edge ML techniques. * Experience with logistics, freight, or broader supply chain datasets and use cases. * Deep expertise in one or more of: transformer architectures (including for structured data), unsupervised learning on structured data, or advanced forecasting methods. * Track record of publications, conference talks, or notable open source / code portfolio demonstrating ML innovation. * Experience building and operating LLM\-powered applications and tools (e.g., via OpenAI APIs, Cursor, or similar frameworks). * Track record of publications, conference talks, or notable open source / code portfolio demonstrating ML innovation. * Experience building and operating LLM\-powered applications and tools (e.g., via OpenAI APIs, Cursor, or similar frameworks).