Lead Data Scientist - Freight Intelligence United States - Remote

Vantora; Northern (KY); Remote; USD 150,000 - 190,000; Full time

Benefits offered by this job

Ownership of core product

Production ownership from day one

Fully remote team

Equity

Healthcare

Flexible PTO

Job summary

Overroute builds AI agents for freight operations and empowers operators with agent-first data science. As Lead data scientist, you set the technical direction for data science, build tools our agents call, and deploy models and tools in production for large fleet operators.

You will own end-to-end work from baseline to production monitoring, working directly with operators to ensure real-world impact and scalability. This is a senior individual contributor role with ownership culture.

Qualifications

• 5+ years hands-on data science, from problem definition to first production release.
• Agent-first workflow with analysis, experiments, pipelines, and evaluation code.
• Strong Python and SQL, with maintainable software practices.
• Experience diagnosing failures in multi-step LLM and agent workflows.
• Experience building reliable datasets and labels when source data is missing.
• Ability to explain model limits to engineers and operators.

Responsibilities

• Define ground truth datasets and labels from operational sources.
• Develop predictive models and decision support with product, engineering, and operators.
• Deploy production models at scale with monitoring, retraining, validation, and updates.

Skills

Python

SQL

Production ML

Experimentation

LLM workflows

Tools

LangSmith

Arize Phoenix

Job description

About Overroute:

Overroute builds AI agents for freight operations. Our agents work inside the tools operators already use, such as email and chat, to track shipments, answer operational questions, communicate with drivers, set appointments, and draft customer communications for freight carriers.

The role:

As Lead data scientist, you set the technical direction for data science at Overroute. Youʼll build the tools our agents call, choose the methods, and build, deploy, and scale the models and tools behind it in production for large fleet operators.

You will work with deep, real-world operating data from day one, alongside the operators who use the product, and own your work end to end, from first baseline through production monitoring. This is a senior individual contributor role. You

lead through technical ownership and hands-on delivery rather than by managing a team, and you decide when a model is ready to ship. You work agent-first: AI coding and data agents are part of how you do data science every day, so one

person can cover the ground of a team.

What you'll own:

• Reliable datasets and labels. Define ground truth from operational sources that may disagree or be incomplete, and build datasets for evaluation and modeling.


• Predictive modeling and decision support. Work with Product, Engineering,and operators to turn freight problems into models and tools that support operational decisions.


• Production models at scale. Take models from the first baseline to an initial production release and scale them in live workflows, partnering with Engineering on evals, deployment and infrastructure. Own automated monitoring, retraining, validation, and model updates, balancing accuracy, response time, reliability, and cost.

How we work:

• Simplest method first. Compare quality, response time, and cost against simpler alternatives. A model earns complexity by beating a published baseline.


• Ground truth before models. Define the label before training or grading anything.


• Language models do not do the math. Calculations come from deterministic code.


• One platform, many customers. Customer differences are configuration, not code branches.


• Clear ownership. Engineering owns data pipelines, infrastructure, and security implementation. You own labels, methods, models, and evaluation. Product owns priorities, customer policy, and approval requirements.


• Make uncertainty clear. Work with Product and Engineering to make each prediction's confidence, limitations, and missing inputs clear to operators.


• Measure customer impact with Product. Connect model accuracy to operational outcomes and customer return on investment ROI. Compare outcomes against a baseline and account for the cost of running and maintaining the models.

What you bring:

• 5+ years of hands-on experience in data science or applied machine learning, including independently taking models from problem definition to a first production release and scaling them in live use. You have automated model updates and connected model accuracy to customer ROI.


• An agent-first way of working. You already hand analysis, experiments, pipelines, and evaluation code to AI agents, check what they produce, and can show a workflow where agents let you do the work of several people. The math in our product still comes from deterministic code; agents are how you build and verify it faster.


• Strong Python and SQL, sound software practices, and model and evaluation code others can maintain.


• Comfortable diagnosing failures in multi-step LLM and agent workflows, end to end.


• Working depth in statistics, experimental design, and predictive modeling, including uncertainty, leakage, biased samples, and data that changes over time.


• Experience building reliable datasets and labels when source systems disagreed or data was missing.


• Judgment to choose the simple method, investigate the surprising result, and stop an approach that is not helping users.


• The ability to explain a model's limits to an engineer and to an operator, and to turn what an operator tells you into a testable problem.

Nice to have:

• Experience at an early-stage company; freight, logistics, or other physical operations; agent tracing tools such as LangSmith or Arize Phoenix.

What we offer:

• Ownership of a core part of the product, with a direct line to the founders on product and company strategy.


• Production ownership from day one: your models run live on real-world freight operating data.


• A fully remote, distributed team. Some travel may be required.


• Competitive compensation and meaningful early-stage equity.


• Healthcare, standard benefits, and flexible PTO.Lead Data Scientist