MaintainX - Senior Applied Scientist, Parts Intelligence & Inventory Optimization

• Own and evolve the optimization and ML models that power Parts Agent capabilities: reorder point prediction, economic order quantity, multi-site stock balancing, and demand forecasting. • Design and implement increasingly sophisticated inventory intelligence: vendor lead time modeling, criticality-weighted safety stock, substitution graph traversal, and proactive stockout alerting. • Build and maintain APIs and tools that expose these models to GenAI agent workflows (tool calling, structured input/output), enabling the Parts Agent to take grounded, explainable actions. • Partner with PM and design to translate messy real-world inventory problems into tractable models, and push back when "optimal" isn't what operators actually want. • Iterate with real users via design partnerships and pilot deployments. Take feedback from parts managers and procurement teams seriously and reflect it back into the model. • Contribute to the surrounding Python service: performance, observability, testing, and reliability of the inventory intelligence runtime. • Help shape how parts intelligence integrates with the broader MaintainX product over time, including learning from historical usage and purchasing data to continuously improve model inputs. • 5+ years of professional software engineering or data science experience, with significant time spent on optimization, forecasting, or ML systems shipped to real users. • Strong fluency with at least one optimization paradigm (LP/MILP, stochastic programming, simulation) and practical experience with demand forecasting or inventory management models. • Solid Python service engineering: APIs, async, testing, profiling, observability. You can own a production service end-to-end. • Academic grounding in Operations Research, Industrial Engineering, Supply Chain, Statistics, or a related quantitative field; strong undergraduate foundation at minimum. • Track record of iterating data-driven systems with real users — you've felt what happens when a model recommendation gets rejected and you've redesigned the approach in response. • Product mindset and delivery orientation: you ship, you measure, you iterate. You care about the operator outcome, not just the metric. • Comfort with ambiguity. You can co-design the data model and feature schema with the team rather than waiting for a clean spec. • Familiarity with GenAI tooling (LLM tool calling, structured output, prompt design for constrained generation) is expected.