Role Overview
Kinaxis is a global leader in modern supply chain orchestration, building an AI-infused platform called Maestro for end-to-end supply chains. The Machine Learning/Operations Research Platform Engineer builds infrastructure and software for training, deploying, scaling, monitoring, and using ML models and optimization algorithms in supply chain applications while contributing to the algorithms.
Responsibilities
- Investigate novel techniques combining leading heuristics with optimization and ML.
- Translate real-world supply chain management use cases into mathematical models.
- Lead design and implementation of mathematical models and ML systems.
- Define test strategies and develop comprehensive test plans.
- Write unit, integration, and debugging tests for robust software.
- Design, develop, and maintain automated test scripts for functional, regression, and performance testing.
- Collaborate with agile team members and stakeholders.
Requirements
- MSc or PhD in Computer Science, Machine Learning, Operations Research, Engineering, or related field.
- 3+ years software development experience, track record of delivering commercial software.
- Working knowledge of C++, including object-oriented design and design patterns, unit testing.
- Experience building and maintaining distributed services and frameworks in C++ and Python.
- Experience deploying and operating ML or optimization workloads in cloud or containerized environments.
- Knowledge of data structures and algorithms, desire to apply them in the real world.
- Working knowledge of mathematical optimization and mixed-integer programming concepts.
- Familiarity with commercial optimization solvers (Gurobi, Xpress, CPLEX) and their application in production systems.
- Ability to design, develop, and maintain automated test scripts for functional, regression, and performance testing.
- Ability to find opportunities to accelerate the SDLC through innovative application of AI or other tooling while upholding architecture consistency, secure design, and code-quality standards.
- Ability to review AI-generated code rigorously for correctness, architectural fit, integration risk, and edge case support with a growth mindset and bias for experimentation.