Technical Lead Manager, Machine Learning

Veho•New York, NY

3d•$210,000 - $240,000

About The Position

Veho's Data Science team is core to Veho's ability to deliver millions of packages by creating the systems that drive forecasting, pricing, and routing decisions and understand on-road delivery behavior. You and your team will own a large part of this scope by turning messy operational reality into production models that make millions of decisions a day and directly move Veho's cost, speed, and service metrics. Your focus will be on our Last Mile Routes : understanding what factors influence our package delivery success, improving our estimates of all aspects of a delivery route including drive- and stop-time. As the Technical Lead Manager you’ll collaborate closely with Product teams to decide which problems should be prioritized and ship reliable production systems that drive improvements to company performance. You and your team are measured by impact on key company metrics, via models that run in production and change how the network operates. You will manage your team of Data Scientists and contribute significantly by writing code, reviewing designs and modeling approaches, and setting the technical bar for model quality and production readiness. You'll help your team adopt AI-assisted development and help set the standard for how the Data Science team leverages AI to iterate on models faster.

Requirements

Bachelor's Degree plus at least 6 years of experience in Machine Learning Engineering or Data Science, or Master's Degree plus at least 4 years:
hands-on experience building, deploying, and owning ML models in production end to end, not handed off to a separate engineering team
depth in relevant modeling domains: time-series forecasting, causal inference, telemetry analysis.
experience managing impactful, high-velocity applied ML / data science teams in smaller-scale companies
experience leveraging AI to accelerate development and analysis
Strong knowledge of Cloud-based data science tooling (AWS preferred) and Data Warehouses (Redshift, Databricks, Snowflake).
Strong knowledge of production ML practices: experimentation, model monitoring, retraining, and working alongside an ML platform / MLOps team
Strong proficiency in Python.
Knowledge of building systems in a Supply Chain setting, enabling a physical supply chain to run like clockwork.

Nice To Haves

Is an expert in their craft and enjoys personally building and shipping impactful machine learning models to production.
Understands their business areas deeply by understanding the data in detail and being a strong collaborator with Product and Operations teams to understand their world.
Creates impact by running the right experiment or building the right model to address a problem or opportunity, balancing short-term impact against the long-term modeling vision.
Applies their ML knowledge to suggest new methods, tools, and approaches that measurably improve the team's models.
Has experience driving managing teams of data scientists / ML engineers, and knows how to drive team velocity by developing the current team's careers, hiring strong new talent, and adopting AI as a core part of how the team builds and iterates on models.
Has experience applying their craft in relevant business areas such as Telemetry data, sales & operations plan forecasting, or other supply chain settings.

Responsibilities

Lead and grow a team of six data scientists / applied ML engineers building production models across route success, last mile route building, and forecasting.
Deeply understand the highest-leverage problems, partner with your team to choose the ML / OR methodologies, and drive models from the first prototype through deployment, monitoring, and iteration.
Ship and maintain production systems. You'll personally build, deploy, and maintain models in production. You stay in the codebase, review your team's PRs, and debug a failing model or a broken pipeline yourself when needed.
Partner closely with the ML Platform / ML Operations team so models deploy on stable infrastructure, and push modeling requirements back into the platform so the next project is faster.
Drive AI usage across the modeling workflow. Set standards, introduce patterns, and drive adoption of how to leverage AI in data science work (EDA, feature and model iteration, ML methodologies).
Be part of the on-call rotation for our data science production systems.