---
title: 'Machine Learning Research Engineer, Model Evaluation at WindBorne Systems'
canonical: 'https://feeny.ai/job/machine-learning-research-engineer-model-evaluation-windborne-systems-redwood-tsv5yt81h2v0'
type: 'job'
last_seen: '2026-09-07'
---

# Machine Learning Research Engineer, Model Evaluation at WindBorne Systems

- **Company:** WindBorne Systems
- **Location:** Redwood City, CA
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-07-13
- **Last confirmed live:** 2026-09-07
- **Apply:** https://jobs.ashbyhq.com/windborne-systems/17c1e7b1-1a8d-4bfd-bd25-3ae48641b642

## Job description

## MACHINE LEARNING RESEARCH ENGINEER, MODEL EVALUATION

WindBorne Systems is supercharging weather forecasts with a proprietary data source: a global constellation of next-generation smart weather balloons targeting critical atmospheric data. We design, manufacture, and operate our own balloons, using their observations to generate otherwise unattainable weather intelligence.

Our mission is to eliminate weather uncertainty and help humanity adapt to climate change—whether by predicting hurricanes or speeding the adoption of renewables. The founding team of Stanford engineers was named Forbes 2019 30 Under 30 and is backed by top-tier investors, including Khosla Ventures and Footwork VC.

WindBorne builds AI weather models that run 24/7, producing global forecasts every 20 minutes. Evaluating these models is much harder than producing a headline accuracy number: performance varies across regions, lead times, weather regimes, and customer use cases, while standard metrics often fail to capture what makes a forecast meteorologically sound or useful.

We need someone with excellent scientific taste to determine where our models excel, where they fail, and which results we should trust. You will work at the intersection of machine learning and meteorology, combining fast analyses with robust systems that make future research faster and more reliable.

## RESPONSIBILITIES

## WHAT YOU’D OWN:

- Evaluation strategy — Work with our Meteorology team to develop a rigorous, meteorologically valid strategy for comparing WeatherMesh with leading AI and physics-based models. Choose the metrics, datasets, baselines, and case studies that provide an honest picture of forecast quality.
- Fast feedback and durable systems — Build quick evaluations that give researchers useful signals, then turn recurring analyses into reliable, reusable infrastructure. Think systematically about reproducibility, provenance, and how evaluation tools fit into the broader research workflow.
- Agentic tooling for evals — Improve our existing evaluation infrastructure, including agentic AI-based tools for investigating forecasts and synthesizing results.
- Technical communication — Produce clear scorecards, visualizations, and explanations for researchers, leadership, customers, and external partners. Communicate model performance precisely, including uncertainty and important caveats.

## SKILLS AND QUALIFICATIONS

## REQUIREMENTS

- Excellent scientific judgment and healthy skepticism. You ask whether a comparison is fair, what else could explain a result, and what evidence would change your mind.
- Strong experimental taste: you can identify the evaluation that answers the question that matters and distinguish robust improvement from noise.
- Systems thinking: you can solve today’s problem while recognizing what should become reusable infrastructure for future work.
- Experience evaluating ML systems using large, scientific, geospatial, multidimensional, or time-series datasets.
- Strong Python skills and experience with scientific and ML tools such as PyTorch, NumPy, pandas, or xarray.
- Able to investigate ambiguous results independently, synthesize evidence, and communicate conclusions clearly.
- Experience with weather, climate, forecasting, physical science, or AI-assisted research tools is helpful, but not required.

## BENEFITS

- 401(k)
- Dental, health, and vision insurance
- Unlimited PTO
- Stock Option Plan
- Office food and beverages

## SALARY

- $140k–$240k. We consider a range of backgrounds and experience levels and adjust offers to be competitive with market rates.

## LOCATION

1600 Bridge Pkwy, Redwood City, CA. Hybrid or in-person.

## About WindBorne Systems

## Company Overview
- **One-liner**: WindBorne Systems designs, builds, and operates the world’s largest constellation of autonomous, long‑duration weather balloons to capture unique in‑situ atmospheric data and deliver AI‑powered weather forecasts.
- **Entity Type**: Private (Series A – total funding $26M)
- **Headquarters**: Redwood City (Redwood Shores), California, United States
- **Founded**: 2019
- **Founders**: John Dean (CEO), Andrey Sushko (CPO), Kai Marshland (CTO)

## Core Business
- **Primary industry**: Aviation & Aerospace / Weather Intelligence
- **Target customers**: B2B, B2G – governments, utilities, airlines, renewable energy operators, and commercial enterprises with weather‑sensitive operations
- **Mission**: Build a planetary nervous system that covers 100% of the Earth, providing humanity with unprecedented environmental data and predictions to mitigate the impacts of weather uncertainty and climate change [windbornesystems.com/mission](https://windbornesystems.com/mission)

## Products & Services
- **Atlas Balloon Constellation**: A global fleet of long‑duration smart weather balloons that autonomously control altitude and provide ~50 vertical profiles per balloon, reaching remote oceans and polar regions [windbornesystems.com](https://www.windbornesystems.com/)
- **WeatherMesh**: A proprietary deep‑learning forecast model that fuses Atlas balloon data with other sources to produce forecasts that surpass the accuracy of both physics‑based and other AI models [windbornesystems.com](https://www.windbornesystems.com/)
- **Data‑as‑a‑Service (DaaS)**: Access to real‑time and historical atmospheric profiles from the balloon constellation, sold to governments and commercial partners
- **SaaS (API)**: AI‑based weather forecasts delivered via API, enabling customers to build actionable insights and automations

## Market Standing
- **Valuation / Market Cap**: Not publicly disclosed
- **Key Metric**: Total Funding – $26M across 6 rounds (including a $15M Series A, per news reports, and a $5M venture round led by the Bill & Melinda Gates Foundation in December 2024) [linkedin.com/company/windborne](https://www.linkedin.com/company/windborne)
- **Notable Investors / Partners**: Pear VC, Khosla Ventures (seed), Bill & Melinda Gates Foundation (venture round); partnerships with U.S. and international governments, private‑sector companies, and philanthropic organizations [windbornesystems.com](https://www.windbornesystems.com/)
- **Growth Signals**: 72 employees (+75.5% YoY); 38 active job postings (+1167% YoY); operations in 8 countries (US, Canada, Poland, Singapore, South Korea, Nigeria, Sweden, Kenya); hundreds of balloons launched per month with global scaling underway [linkedin.com/company/windborne](https://www.linkedin.com/company/windborne)

## Competitive Advantages
- **Proprietary data moat**: In‑situ atmospheric data from regions (oceans, poles) where other sensors are scarce – a key input for improving forecast accuracy.
- **Vertically integrated hardware & software**: In‑house design, manufacturing, and AI model development, all based in the USA.
- **First‑mover scale**: Only company operating a long‑duration, controlled‑altitude balloon constellation at this scale (Atlas).
- **Proven model performance**: WeatherMesh consistently outperforms traditional physics‑based and other AI forecast models, validated by government and commercial partners [windbornesystems.com](https://www.windbornesystems.com/)

## Strategic Focus
- Scale the Atlas constellation to permanently close atmospheric data gaps pole‑to‑pole.
- Expand federal and commercial sales (DaaS and SaaS), especially to utilities and the U.S. government.
- Advance WeatherMesh accuracy and develop new use cases in aviation routing, renewable energy grid optimization, and disaster response [windbornesystems.com/mission](https://www.windbornesystems.com/mission)

## Why Work Here
- **Planetary impact**: Every line of code and hardware design directly improves weather prediction, saves lives, and advances climate science.
- **Engineering culture**: “The Loonie Way” – high agency, obsessive problem‑solving, building from scratch, and iterating relentlessly. The team includes alumni from Project Loon, Stanford, and top aerospace/tech companies [windbornesystems.com/careers](https://windbornesystems.com/careers).
- **Hard problems**: Autonomous systems in extreme environments, real‑time data pipelines, and cutting‑edge AI.
- **Work environment**: Based in Redwood Shores, CA; technology is invented, designed, and manufactured in the US. Roles are likely on‑site (many engineering and operations positions specify location). Offices are collaborative and mission‑focused.
- **Growth**: 38 open roles across engineering, operations, business development, and more – a fast‑scaling startup with multi‑year runway [windbornesystems.com/open-roles](https://windbornesystems.com/open-roles).

## Sources
1. [windbornesystems.com](https://www.windbornesystems.com/)
2. [windbornesystems.com/careers](https://windbornesystems.com/careers)
3. [windbornesystems.com/mission](https://windbornesystems.com/mission)
4. [linkedin.com/company/windborne](https://www.linkedin.com/company/windborne)
5. [windbornesystems.com/open-roles](https://windbornesystems.com/open-roles)

## Other roles at WindBorne Systems

- [Senior Manufacturing Engineer](https://feeny.ai/job/senior-manufacturing-engineer-windborne-systems-redwood-city-5397fj657a1r) — Redwood City, CA
- [Part Time Launch Operator - Corpus Christi](https://feeny.ai/job/part-time-launch-operator-corpus-christi-windborne-systems-corpus-christi-ky630jzb75vp) — Corpus Christi, TX
- [Launch Contractor - Uruguay](https://feeny.ai/job/launch-contractor-uruguay-windborne-systems-artigas-ppsys5pjm21j) — Artigas, Uruguay
- [Electrical Engineer Intern](https://feeny.ai/job/electrical-engineer-intern-windborne-systems-redwood-city-yxanrb2he2m7) — Redwood City, CA
- [Launch Operator-Alabama](https://feeny.ai/job/launch-operator-alabama-windborne-systems-alabama-4gje76g48nar) — Alabama
- [Lead Software Engineer - Gov Platforms](https://feeny.ai/job/lead-software-engineer-gov-platforms-windborne-systems-redwood-city-kqax9vq276dy) — Redwood City, CA
- [Meteorological Scientist - Data Assimilation and NWP](https://feeny.ai/job/meteorological-scientist-data-assimilation-and-nwp-windborne-systems-redwood-a2hymqfcy4tc) — Redwood City, CA
- [GTM Lead](https://feeny.ai/job/gtm-lead-windborne-systems-redwood-city-2v2gtspff59v) — Redwood City, CA
- [Chief of Staff to the CEO](https://feeny.ai/job/chief-of-staff-to-the-ceo-windborne-systems-redwood-city-r8q66bc40411) — Redwood City, CA
- [Machine Learning Infrastructure Engineer](https://feeny.ai/job/machine-learning-infrastructure-engineer-windborne-systems-redwood-city-chps5jyh06x9) — Redwood City, CA