Staff Data Scientist

Stord; United States; On-site; USD 120,000 - 160,000; Full time

Job summary

Stord is seeking a Staff Data Scientist to enhance their cloud-based supply chain platform. This role involves tackling complex modeling challenges, developing predictive models, and collaborating with engineering to integrate these models into production systems.

The ideal candidate will have expert-level Python and SQL skills, a deep understanding of machine learning, and experience with ML operations practices. You’ll engage directly with leadership to shape Stord's data science strategy.

Qualifications

• Expert-level Python programming with production code experience.
• Strong SQL skills with Postgres and BigQuery experience.
• Deep understanding of statistical analysis and machine learning fundamentals.
• Proven experience deploying and operating models in production.

Responsibilities

• Own complex modeling problems from framing to deployment.
• Conduct exploratory data analysis.
• Build predictive models for optimization and recommendations.
• Integrate models into production systems.

Skills

Expert-level Python programming

Strong SQL skills with Postgres and BigQuery

Statistical analysis and machine learning fundamentals

ML ops practices

Cloud platforms (AWS, GCP, or Azure)

Git/GitHub proficiency

Job description

Stord is a consumer experience company that powers seamless checkout through delivery for today’s leading brands.

About the Staff Data Scientist Position

Stord is revolutionizing the logistics industry with its cloud‑based supply chain platform. We empower brands to compete and grow by providing end‑to‑end logistics solutions coupled with modern tools across Order Management, Warehouse Management, Consumer Experience, Demand Planning, and more. As we continue to enhance our platform, we are doubling down on data and ML to make our services even more powerful.

We are seeking a Staff Data Scientist to serve as a technical anchor across our data science efforts. This senior individual‑contributor role focuses on the most difficult and highest‑impact problems, drives the direction of our data science and ML technology stack, and sets standards and best practices alongside data scientists and ML engineers. You will work directly with engineering teams embedded in product development and will regularly engage with leadership to shape our data science strategy.

What You’ll Do

Tackle the Hardest Problems

• Own the most complex, ambiguous, and high‑stakes modeling problems end‑to‑end, from initial framing through production deployment.
• Conduct deep exploratory data analysis to validate assumptions and surface non‑obvious insights.
• Build predictive models for supply chain optimization and consumer‑facing applications, including delivery time estimation, demand forecasting, routing optimization, personalized product recommendations, and customer profile enrichment and segmentation.
• Write production‑quality code that integrates cleanly with existing services and can be maintained by others.

Drive the Technology Stack & Standards

• Play a leading role in defining Stord’s data science and ML technology stack, tooling, and infrastructure choices.
• Work alongside data scientists and ML ops to establish standards and best practices for model development, deployment, monitoring, and retraining.
• Contribute to both the data science and ML ops sides of the stack as needs arise.
• Document technical decisions and patterns so the broader team can build on them.

Partner Directly with Engineering

• Embed with engineering teams to integrate models into production systems and ship features.
• Deploy models as microservices or API endpoints and own their performance over time.
• Participate in sprint planning and agile ceremonies.
• Review code and provide feedback on data‑related implementations.

Engage with Leadership

• Lead technical conversations with engineering and product leadership on data science strategy and investment.
• Translate complex modeling approaches and trade‑offs into clear, actionable recommendations for non‑technical stakeholders.
• Identify high‑leverage opportunities for data science across the platform and bring them forward with supporting analysis.

What You’ll Need

Required Technical Skills

• Expert‑level Python programming with production code experience
• Strong SQL skills with Postgres and BigQuery experience
• Deep understanding of statistical analysis and machine learning fundamentals
• Proven experience deploying and operating models in production environments, including monitoring and retraining
• Hands‑on experience with ML ops practices: model versioning, pipeline orchestration, drift detection, and experimentation frameworks
• Experience with cloud platforms (AWS, GCP, or Azure)
• Proficiency with Git/GitHub and collaborative development workflows

Required Soft Skills

• Technical credibility – earns trust as the expert on hard problems through demonstrated depth, not just seniority
• Communication – carries technical opinions clearly into leadership conversations and can make complex trade‑offs legible
• Pragmatism – focuses on delivering working solutions and iterates; doesn’t wait for perfect conditions
• Collaborative – works openly with data scientists, ML engineers, and software engineers toward shared outcomes
• Self‑directed – identifies what needs to be done in ambiguous situations without waiting for detailed specs

Preferred Qualifications

• Background in logistics, supply chain, or e‑commerce domains
• Experience building recommendation systems or customer profile modeling at scale
• Experience with real‑time model serving and high‑availability ML systems
• Experience with Elixir, TypeScript, or functional programming paradigms
• Familiarity with Kubernetes, CI/CD, and DataOps tooling
• Experience helping define standards or tooling choices across a data science team