Overview You will be responsible for building and deploying machine learning models and AI-driven assistants that interpret structured operational data, predict risks, and drive smarter decision-making in asset-heavy environments. Responsibilities Develop predictive models for asset health and risk scoring based on structured logs and operational histories. Build intelligent assistants that query and interpret historical operational data and maintenance records. Design scalable feature engineering pipelines and deploy models into a modern SaaS architecture. Collaborate closely with engineering and product teams to integrate AI insights into user-facing applications. Requirements Strong applied machine learning skills (Python, Scikit-learn, TensorFlow, or PyTorch). Familiarity with time-series forecasting, predictive modeling, or risk scoring techniques. Experience working with structured data APIs, SQL databases, and RESTful services. Hands-on experience designing prompts or workflows for large language models (LLMs) interacting with structured or semi-structured data. Basic MLOps practices: model versioning, deployment, and monitoring. Nice to Have Background in industrial engineering, predictive maintenance, or asset management. Experience with asset-intensive environments (manufacturing, energy, healthcare, research labs). Exposure to agent-based AI architectures (LangChain, LangGraph, CrewAI, Time-Series models). Who Are You Comfortable working autonomously in a fast-moving, early-stage team. Highly pragmatic: You know when a quick MVP is better than a perfect academic solution. Eager to build foundational IP that solves real-world industrial problems. excellent in communication and academic writing.

#J-18808-Ljbffr