Job description

Who We Are & Why Join Us Avathon is the leading Industrial AI autonomy platform, helping customers across heavy industries -- energy, mining, manufacturing, aerospace, defense, and logistics -- accelerate the journey toward autonomous operations. Our platform is built on a Computational Knowledge Graph foundation that contextualizes and connects operational data across siloed systems, bringing together time series, structured, unstructured, and machine vision data to power AI-driven applications in asset performance management, supply chain intelligence, visual AI, and global trade management. With capabilities spanning digital twins, normal behavior modeling, natural language processing, and computer vision, Avathon delivers real-time predictive intelligence and agentic decision-making at industrial scale. Cutting-Edge AI Innovation -- Join a team at the forefront of AI, developing groundbreaking solutions that shape the future. High-Growth Environment -- Thrive in a fast-scaling startup where agility, collaboration, and rapid professional growth are the norm. Meaningful Impact -- Work on AI-driven projects that drive real change across industries and improve lives. Learn more at: avathon.com We are hiring a Senior AI Scientist to build the optimization and machine learning models behind Logistics and Transportation on the Avathon platform. You will work on routing, scheduling, network optimization, ETA prediction and asset utilization across FTL, LTL, intermodal and maritime networks, including vessel scheduling and container repositioning. Our models run on top of a Computational Knowledge Graph that links shipments to the orders, parts and production they affect, so you can measure impact, not just delay. This role sits in Product Engineering. You will take models from research to production with the Logistics engineering team. You Will Optimization Build fleet optimization, capacity planning and vehicle routing and scheduling models (VRP and its variants) with real constraints such as time windows, capacity, regulations and SLAs Solve maritime and container problems, including vessel scheduling, port operations and container repositioning Combine OR, reinforcement learning and ML where a single method falls short Prediction Build ETA and transit time models by lane, mode, carrier and season, using shipment events, GPS and telematics, weather and port congestion Flag shipments, carriers and suppliers that move away from normal behavior, and forecast clear-to-build risk days in advance Model the trade-off between expedite cost and production impact so recommendations make business sense Productization and Leadership Put models into production with engineering on cloud-native services, with monitoring, explanations and data validation Use graph features from the Computational Knowledge Graph and work with AI agents that triage exceptions and recommend actions Lead AI initiatives in the domain, mentor scientists and help product set the roadmap You'll Have PhD in Operations Research, Computer Science, Applied Math, Transportation Engineering or a related field 10+ years in AI, ML, optimization or supply chain systems Deep knowledge of routing algorithms (VRP, shortest path, heuristics and metaheuristics) and time series and probabilistic forecasting Hands-on Python (NumPy, pandas, PyTorch or TensorFlow) and optimization solvers (Gurobi, CPLEX, OR-Tools) Experience shipping models to production on real logistics data, ideally at a TMS, visibility or freight vendor such as Oracle, Blue Yonder, Manhattan, project44, FourKites or Flexport, or at an industrial shipper Maritime, container logistics or fleet scheduling experience is a strong plus Reinforcement learning, simulation or digital twins, and streaming data (Kafka, Spark) are a plus Publications at NeurIPS, ICML, INFORMS or similar are a plus Compensation Pay Range: $160k - $240k salary annually. Pay for this position is based on a number of factors including geographic location and may vary depending on job-related knowledge, skills, and experience. Location: This role is not remote. Candidates must be based in the Bay Area, CA and are expected to report to our Pleasanton office 5 days a week. Avathon is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, pregnancy, genetic information, disability, status as a protected veteran, or any other protected category under applicable federal, state, and local laws. Avathon is committed to providing reasonable accommodations throughout the recruiting process. If you need a reasonable accommodation, please contact us to discuss how we can assist you.

Requirements

Must-haves

Who We Are & Why Join Us
Learn more at: avathon.com
Optimization
Build fleet optimization, capacity planning and vehicle routing and scheduling models (VRP and its variants) with real constraints such as time windows, capacity, regulations and SLAs
Solve maritime and container problems, including vessel scheduling, port operations and container repositioning
Combine OR, reinforcement learning and ML where a single method falls short
Build ETA and transit time models by lane, mode, carrier and season, using shipment events, GPS and telematics, weather and port congestion
Flag shipments, carriers and suppliers that move away from normal behavior, and forecast clear-to-build risk days in advance
Model the trade-off between expedite cost and production impact so recommendations make business sense
Productization and Leadership
Put models into production with engineering on cloud-native services, with monitoring, explanations and data validation
Use graph features from the Computational Knowledge Graph and work with AI agents that triage exceptions and recommend actions
Lead AI initiatives in the domain, mentor scientists and help product set the roadmap
PhD in Operations Research, Computer Science, Applied Math, Transportation Engineering or a related field
10+ years in AI, ML, optimization or supply chain systems
Deep knowledge of routing algorithms (VRP, shortest path, heuristics and metaheuristics) and time series and probabilistic forecasting
Hands-on Python (NumPy, pandas, PyTorch or TensorFlow) and optimization solvers (Gurobi, CPLEX, OR-Tools)
Experience shipping models to production on real logistics data, ideally at a TMS, visibility or freight vendor such as Oracle, Blue Yonder, Manhattan, project44, FourKites or Flexport, or at an industrial shipper
Maritime, container logistics or fleet scheduling experience is a strong plus

Nice-to-haves

Reinforcement learning, simulation or digital twins, and streaming data (Kafka, Spark) are a plus
Publications at NeurIPS, ICML, INFORMS or similar are a plus

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aimachine learningmlpython

Platform: greenhouse
Effort: quick

Benefits

Benefits detected in the listing.

Vision