Collaborate with a cross-functional team (designer, product strategy, solution architects) to improve and optimize Monte Carlo–based simulation algorithms for predictive maintenance planning.
Analyze, refactor, and optimize existing Python code to ensure performance, scalability, and adherence to best practices.
Benchmark algorithm performance at component and system levels under varying data volumes and hardware configurations (CPU vs GPU).
Design and execute experiments to evaluate the feasibility of large-scale simulation deployments on cloud environments (Azure preferred).
Develop proof-of-concept data workflows, including parameterized simulations, scenario scaling, and distribution-based reporting.
Contribute to defining the Minimum Viable Architecture (MVA), including cost assessment, hardware/software requirements, and integration pathways.
Produce technical deliverables: benchmark reports, code optimization documentation, cost/performance trade-offs, and recommendations for next phases.
Work closely with solution architects and fellow data scientists; translate simulation results into actionable insights for product and service offerings.
Travel for team and client meetings, typically up to 15%.
Requirements
Master’s or PhD in Computer Science, Data Science, Applied Mathematics, Operations Research, or a related field.
3–5+ years of professional experience in data science, computational modeling, or applied research (industry or advanced research projects).
Strong proficiency in Python, including code optimization, profiling, and use of libraries for scientific computing (NumPy, SciPy, pandas, Dask, Numba, etc.).
Experience with Monte Carlo simulation methods or other stochastic modeling techniques.
Familiarity with high-performance computing (parallelization, GPU acceleration, CUDA, RAPIDS, or equivalent).
Hands-on experience with cloud platforms (Azure preferred, AWS or GCP acceptable), including resource provisioning, scalability, and cost management.
Understanding of data architecture principles and ability to work with large, complex datasets.
Experience in building data-driven reports and visualizations (e.g., matplotlib, Plotly, Dash, or equivalent).