Senior Applied Data Scientist — Forecasting & Decision Systems
Location: Oahu, Hawaiʻi
Work Arrangement: Hybrid, with regular time alongside corporate, warehouse, merchandising, and field teams
Role Summary
Hawaiʻi’s largest food distribution company is seeking a Senior Applied Data Scientist to build forecasting, optimization, and AI-enabled decision systems across a complex, real-world logistics environment.
Your first major mission will be to lead the development of HFA’s forecasting applications —from defining the scientific baseline and testing competing approaches to building a working product, deploying forecasts into operational workflows, and measuring whether recommendations improve real business outcomes.
This role sits at the intersection of applied science, software development, and operational decision-making. You will use modern AI-assisted development tools to move quickly from hypothesis to model to working application, while maintaining the testing, documentation, security, and engineering discipline required for production systems.
Over time, your work may expand into inventory and ordering optimization, routing and scheduling, promotion effectiveness, computer vision, and AI-first monitoring platforms that identify emerging issues and help teams act earlier.
What You’ll Do
- Own HFA’s demand forecasting capability from problem framing through production deployment, monitoring, and continuous improvement
- Develop store-item-day forecasts that account for seasonality, promotions, intermittent demand, stockouts, product life cycles, and the asymmetric cost of over- and under-ordering
- Establish credible baselines, backtesting methods, business-weighted evaluation metrics, and controlled pilots
- Rapidly prototype working analytical applications, model-review tools, and operational workflows using modern AI-assisted development platforms
- Translate model outputs into usable recommendations for buyers, order writers, merchandisers, and operational leaders
- Build production-quality Python and SQL solutions, including batch pipelines, model services, APIs, monitoring, and decision logs
- Measure whether models produce meaningful business outcomes, including reduced distress, improved shelf availability, better ordering, and more effective allocation of labor and resources
- Design mechanisms to capture user overrides, operational context, and actual outcomes so systems improve over time
- Partner with Data Engineering and Business Intelligence to use and extend governed Snowflake and dbt data products
- Work with Software Engineering to integrate models and decision logic into HFA’s internal applications
- Contribute selectively to analytical datasets, KPI definitions, and dashboards that directly support the decision products you own
- Explore optimization approaches for scheduling, routing, purchasing, replenishment, and task prioritization
- Help develop AI-assisted operational monitoring that detects abnormalities, assembles supporting evidence, explains likely causes, and recommends appropriate next actions with human oversight
- Communicate findings clearly to both technical teams and business leaders, including when the evidence does not support deploying a model
What We’re Looking For
- 5+ years of experience building applied data science, forecasting, machine-learning, or decision-support systems, or an equivalent record of production ownership
- Demonstrated experience taking a model beyond experimentation and into a live business workflow
- Strong Python and SQL skills
- Practical depth in time-series forecasting, including rigorous backtesting and comparison against simple or incumbent baselines
- A scientific mindset grounded in hypothesis testing, measurement, uncertainty, and willingness to revise an approach when the evidence does not support it
- Ability to translate an ambiguous business problem into measurable objectives, constraints, evaluation criteria, and an implementable product
- Experience building working software—not only notebooks—including applications, services, automated pipelines, or internal tools
- Demonstrated use of AI-assisted coding tools to accelerate development while maintaining tests, version control, security, and maintainable architecture
- Experience with production practices such as Docker, orchestration, CI/CD, model monitoring, drift detection, observability, or experiment tracking
- Ability to work directly with operational users, understand how decisions are actually made, and explain technical results in practical terms
- Strong judgment about when to use advanced modeling and when a simpler, more understandable approach is the better solution
- Ability to operate independently while collaborating closely with data, BI, software, and business teams
Preferred Experience
- Demand forecasting in grocery, retail, consumer packaged goods, food distribution, replenishment, or other inventory-intensive environments
- Probabilistic or quantile forecasting, hierarchical forecasting, intermittent demand, cold-start forecasting, and demand censored by stockouts
- Inventory optimization, safety stock, service-level modeling, or newsvendor-style decision problems
- Mathematical optimization, including routing, scheduling, constraint programming, simulation, or mixed-integer programming
- Tools such as OR-Tools, Gurobi, CPLEX, Pyomo, or similar optimization frameworks
- Snowflake, dbt, Airflow, MLflow, Snowpark, or comparable warehouse-centric platforms
- Applied LLM or agentic-system experience, especially systems that use tools, structured data, business rules, and human approval workflows
- Computer vision, image classification, object detection, OCR, or vision-language models
- Causal inference, promotion-lift analysis, difference-in-differences, synthetic controls, or experimentation in operational environments
- Experience developing lightweight front ends or internal applications using React, Streamlit, Dash, or comparable technologies
- Experience with DSD, logistics, warehouse, merchandising, transportation, or multi-location field operations
What Success Looks Like
First 90 Days
- Build a clear understanding of HFA’s ordering process, operating constraints, and current forecasting or replenishment methods
- Establish a reproducible backtesting and evaluation framework
- Reproduce the incumbent baseline and identify the most important sources of forecast error
- Deliver an initial model and working forecast-review prototype for a focused category, customer group, or operating area
First Six Months
- Demonstrate measurable improvement over the existing baseline on appropriate holdout data
- Deploy probabilistic forecasts or order recommendations into a controlled operational pilot
- Implement monitoring, drift detection, model versioning, and user-override capture
- Establish a measurement plan for distress, shelf availability, service level, and operational adoption
First Year
- Measure the operational and financial results of the initial forecasting pilot
- Expand successful approaches to additional categories, customers, or operating areas
- Establish a sustainable model-development and monitoring process
- Deliver or scope a second decision system, such as order optimization, inventory-risk detection, routing, scheduling, or AI-assisted operational monitoring
The first year will remain anchored on forecasting, with additional initiatives sequenced behind demonstrated results rather than pursued simultaneously. This focus is consistent with the original business case’s emphasis on controlled gates and measurable improvement before expanding the model portfolio.
Benefits & Wellness
HFA offers competitive, people-first benefits designed to support you and your ʻohana, including:
- 100% employer-paid medical coverage for team members, with subsidized family coverage
- Dental, vision, and preventive care benefits
- 401(k) retirement plan with up to 4% employer match and immediate vesting
- Paid vacation, sick leave, holidays, and floating holidays
- Employee Assistance Program with free, confidential counseling
- Horizon Day—a paid day off each year to volunteer in the community
- Wellness programs including gym membership discounts and health initiatives
Compensation
Salary Range: $145,000–$180,000 annually
Actual compensation will be determined based on qualifications, relevant production experience, technical depth, and internal equity. This range reflects the anticipated base salary for this Oahu-based role at the time of posting.
Candidates near the upper end of the range will generally bring demonstrated ownership of production forecasting or optimization systems, strong software-development capability, and a record of measurable operational impact.
Why This Role
You will have direct ownership of a new applied-science capability and the opportunity to build systems that influence real orders, inventory, routes, labor, shelves, and customer service across Hawaiʻi.
You will not be starting with an empty data environment. HFA has established ingestion pipelines, a governed Snowflake warehouse, orchestration, reporting systems, and internal applications used by field and operational teams. Your opportunity is to turn those foundations into predictive and prescriptive systems that improve daily decisions.
The work is tangible. When a model succeeds, the result is not simply a more accurate dashboard—it is less wasted product, better shelf availability, more effective operations, and stronger systems supporting the teams that help keep Hawaiʻi fed and moving.
This is not a notebook-only research role or a traditional reporting position. It is a hands-on opportunity for someone who wants to apply scientific thinking, modern AI-enabled development, and strong engineering judgment to meaningful operational problems.
HFA is an equal opportunity employer. Employment decisions are based on qualifications, merit, and business needs.
Job Type: Full-time
Pay: $145,000.00 - $180,000.00 per year
Benefits:
- 401(k) matching
- Dental insurance
- Flexible spending account
- Health insurance
- Life insurance
- Paid time off
- Vision insurance
Application Question(s):
- Do you reside on Oahu currently?
Location:
- Honolulu, HI 96819 (Required)
Work Location: In person
