Lead Data Scientist

• Design, implement, and validate Bayesian models for epidemic situational awareness - renewal-equation and compartmental (SEIR-family) models, Rt estimation, nowcasting under reporting delay, and short-term forecasting.
• Own production modeling pipelines end to end: R and Stan model code, containerized execution, cloud batch orchestration, structured outputs, and run diagnostics.
• Contribute models and evaluation to collaborative forecast hubs, including ensemble construction and scoring across contributing teams.
• Build scenario models and outbreak simulators that quantify the effect of candidate interventions.
• Set the standard for forecast evaluation - proper scoring rules, calibration and coverage, and backtesting against retrospective data.
• Work with surveillance data at source, including its delays, revisions, and biases.
• Communicate uncertainty clearly and honestly to epidemiologists, policy staff, and senior leadership - including where the data don’t support a conclusion.
• Set engineering standards for the team: version control, code review, automated testing, reproducible environments, and open-source release practice.
• Mentor junior and mid-level data scientists, and collaborate with external academic and public health partners.

• Master’s or doctoral degree in Statistics, Biostatistics, Applied Mathematics, Epidemiology, Computational Biology, Operations Research, or a closely related quantitative discipline.
• 8+ years of applied statistical modeling experience, or 5+ with a doctoral degree, including work that went into production or operational use.
• Expert-level R, including writing code others will run and maintain; working production proficiency in Python.
• Demonstrated Bayesian inference experience - Stan, NumPyro, PyMC, or equivalent - including hierarchical models and MCMC diagnostics.
• Direct experience with infectious disease or epidemiological modeling, or equivalent mechanistic modeling of a dynamic process.
• Time-series forecasting with rigorous evaluation: proper scoring rules, calibration, backtesting.
• Experience with messy operational reporting data - delays, right-truncation, revisions.
• Software engineering fundamentals: Git workflow, code review, automated testing, Docker, CI/CD.
• Cloud compute experience; Azure preferred.
• Ability to obtain and maintain a U.S. federal Public Trust or Suitability/Fitness determination.

Nice to have

• PhD with peer-reviewed publications in infectious disease modeling, forecasting, or statistical methodology.
• Hands-on experience with the open-source epidemiological modeling ecosystem - EpiNow2, epinowcast, EpiEstim, scoringutils, or comparable tooling.
• Prior participation in a collaborative forecasting hub as a contributing modeling team.
• Prior federal public health, national laboratory, or federally funded research experience.
• Direct experience supporting an active outbreak response under operational time pressure.
• Public open-source contributions, particularly to statistical or epidemiological software.
• Experience mentoring analysts or leading a small technical team.

This is a full-time, W-2 direct-hire position with JR Software Solutions. It is not available on a corp-to-corp, and we are not able to transfer an existing H-1B or any other employment visa for this role.

What we offer

Competitive salary · medical, dental, and vision coverage · 401(k) · paid time off and holidays · professional development, conference participation, and certification support.

JR Software Solutions Inc. (JRSS) is hiring a Lead Data Scientist to support a federal public health forecasting and outbreak analytics mission in Atlanta, GA. This role is remote within the United States; candidates in the Atlanta metro area are preferred.

This is a modeling role, not a general machine learning role. You will build and maintain the probabilistic models that estimate where an outbreak is now and where it is heading - time-varying reproduction number (Rt) estimates, nowcasts corrected for reporting delay and right-truncation, ensemble forecasts of emergency department visits and hospital admissions, and scenario models that answer specific policy questions. The output goes to senior federal leadership, to state and local health officials, and in many cases to the public.

If you have spent your career fitting Bayesian models to messy surveillance data and then explaining honestly what they can and cannot tell a decision-maker, this is that job.

About JRSS

JRSS is a certified Women-Owned Small Business (WOSB), Small Disadvantaged Business (SDB), and HUBZone company headquartered in Tampa, FL. We deliver Cloud, AI/ML, Big Data and BI Analytics, ERP, and IT program management to Federal Civilian agencies and Fortune 500 clients. Our Data Science practice supports federal public health missions with statistical modeling, forecasting, and decision-support analytics delivered to production standards.