Overview In this role you will own the intelligence layer behind the Parts Agent, shaping optimization and AI-powered tooling to answer critical inventory questions for enterprise maintenance. You will collaborate with product and design to translate real-world inventory problems into tractable models and ship iterative solutions based on customer feedback. Your work will enable scalable, trustworthy decisions across multi-site stock and supplier catalogs. This role blends advanced modeling with production service excellence to impact operations at scale.
Compensation / Benefits Responsibilities- Own and evolve optimization and ML models for Parts Agent: reorder point, EOQ, multi-site stock balancing, and demand forecasting
- Design and implement sophisticated inventory intelligence: lead time modeling, safety stock, substitution graph traversal, proactive stockout alerts
- Build and maintain APIs and tools exposing models to GenAI workflows (tool calling, structured I/O)
- Collaborate with PM and design to translate messy inventory problems into tractable models and push back when optimal differs from operator needs
- Iterate with real users via design partnerships and pilot deployments, incorporating feedback
- Contribute to the Python-based inventory intelligence runtime: performance, observability, testing, reliability
- Help shape how parts intelligence integrates with the broader MaintainX product and learn from historical data to improve inputs
Key requirements- 5+ years in software engineering or data science with optimization, forecasting, or ML systems shipped to real users
- Strong fluency in at least one optimization paradigm (LP/MILP, stochastic programming, simulation) and experience with demand forecasting or inventory models
- Solid Python service engineering: APIs, async, testing, profiling, observability; end-to-end ownership
- Academic grounding in Operations Research, Industrial Engineering, Supply Chain, Statistics, or related quantitative field; strong undergraduate foundation
- Track record of iterating data-driven systems with real users and incorporating feedback
- Product mindset and delivery orientation: shipping, measuring, iterating with operator outcomes in mind
- Comfort with ambiguity and ability to co-design data models and feature schemas
- Familiarity with GenAI tooling (LLM tool calling, structured output, prompt design)
- collaboration across product, design, and data science
- strong communication and stakeholder management
- customer empathy and user-centric problem solving
- optimization (LP/MILP, stochastic programming, simulation)
- demand forecasting and inventory management models
- Python service engineering (APIs, async, testing, profiling)
