Machine Learning (ML) Applications Engineer- Chemical Process Engineering- Hiring multiple

📋 Description

• • Own the end-to-end post-sales deployment of Laminar’s AI-powered optimization models, beginning with Clean-In-Place (CIP) systems and rapidly expanding into energy, water, and waste-reduction workflows across global manufacturing plants.
• • Partner shoulder-to-shoulder with customer process engineers, plant managers, and sustainability teams to map their exact operating conditions, define quantifiable success KPIs (gallons of water saved, kWh reduced, minutes of downtime eliminated), and translate those KPIs into model objectives.
• • Ingest, clean, and analyze high-volume sensor and time-series data from SCADA, historian, and IoT sources; use Python (NumPy, Pandas) and MATLAB to surface patterns, anomalies, and optimization levers that were previously invisible to plant staff.
• • Fine-tune and retrain machine-learning models in Scikit-Learn, TensorFlow, or PyTorch to reflect each facility’s unique recipes, piping layouts, and regulatory constraints—then validate improvements through rigorous A/B testing on live lines.
• • Craft data stories that resonate: build interactive dashboards, concise slide decks, and executive one-pagers that turn complex multivariate results into clear, actionable recommendations for both PhD-level engineers and VP-level business sponsors.
• • Lead on-site workshops and virtual training sessions (10–20 % travel) to install sensors, calibrate models, and upskill customer teams—ensuring every deployment hits promised savings within the first 90 days and drives renewal/expansion revenue.
• • Champion a feedback loop between field performance and R&D: log edge cases, propose new features, and collaborate with data-science, software, and product teams to harden models against process drift and sensor failure.
• • Contribute to internal playbooks, SOPs, and MLOps pipelines so each new customer deployment is faster, safer, and more profitable than the last—directly accelerating Laminar’s path to becoming the default AI layer for process industrials.
• • Stay relentlessly curious: monitor emerging academic research, attend Greentown Labs community events, and pilot next-gen techniques (reinforcement learning, probabilistic programming, differentiable simulators) that can unlock the next 10× efficiency gain for customers like Unilever, Coca-Cola, and AB InBev.
• • Embody the company’s empire-building ethos—move fast, speak up, take ownership, and celebrate wins with a tight-knit team that is as passionate about decarbonizing the planet as it is about shipping bulletproof code.