Tech Stack

Description

You will be instrumental in developing, evaluating, and productionizing a next-gen Dispatch System that fuses short and long-term horizon optimizers to decide who gets which job, when, and why. You'll build prediction models, incorporate them into the optimizer, and lead the team to successful outcomes.

Requirements

• 6+ years experience in ML Engineering with ownership of production systems.
• Expert-level Python.
• Hands-on optimization (Mixed Integer Programming, Linear Optimization, Stochastic Optimization) and modern ML (XGBoost, PyTorch).
• Proven record designing cloud-native pipelines on AWS, GCP, or Azure (AWS preferred).
• Strong SQL, feature-store design, and data-quality mindset.

Responsibilities

• Design end-to-end Python services for batch and streaming, ingesting model outputs and running constrained optimization for real-time dispatch decisions.
• Build/extend ML models (gradient-boosting, deep learning, OR-Tools) and run time-horizon simulations to quantify cost vs. service-level trade-offs.
• Automate training, validation, A/B rollout, and monitoring using SageMaker and Airflow.
• Partner with Product, Ops, and Data Engineering; mentor a small squad of ML engineers; present findings to execs.
• Instrument NPS and cost telemetry, identify failure modes, and iterate on improvements.