Machine Learning Research Engineer

WindBorne Systems

Atlanta (GA)

Hybrid

USD 140,000 - 240,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

401(k)

Health insurance

Unlimited PTO

Stock options

Office snacks

Job summary

WindBorne Systems is seeking a researcher to advance AI-driven weather data assimilation and develop a foundation model for multi-dataset forecasting. You will work with real-time observations from balloons, satellites, and weather stations to improve forecasts and enable scalable, reusable data pipelines.

The role emphasizes deep ML understanding, rapid experimentation, and collaboration across research and engineering to turn findings into practical systems for weather prediction.

Qualifications

Strong research taste and ability to design experiments that answer important questions.
Deep enthusiasm for machine learning and understanding models in detail.
Experience with large, messy datasets and building dependable pipelines.
Able to iterate quickly while thinking about durable infrastructure.
Comfortable crossing boundaries between research and engineering.

Responsibilities

AI-based data assimilation: develop methods to incorporate real-time observations into forecasts.
Foundation model for weather: work toward a single model predicting multiple weather datasets.
Handle messy, large weather datasets: find, clean, combine, and build reusable systems for data use.
Rapid experiments: test ideas quickly and chase 1% model improvements.
Infrastructure and systems: turn experiments into reusable systems for future work.
Research direction: form hypotheses, design experiments, and keep up with ML research.
Venture into operations, data engineering, or other technical tasks as needed to get research working.

Skills

Python

PyTorch

ML systems

Data pipelines

Job description

Responsibilities

What you’d own:

AI-based data assimilation — Develop methods for incorporating real-time observations from balloons, satellites, weather stations, and other sources into our forecasts.
A foundation model for weather — Work toward a single model capable of predicting many weather-related datasets, including variables and data products not covered by traditional global forecasts.
Messy, large weather datasets — Find, understand, clean, and combine large datasets with inconsistent formats, resolutions, coverage, and quality. Determine which data is actually useful and build systems that make it easier to use again.
Rapid experiments — Test ideas quickly, learn from failures, and follow promising results into the weeds and chase down another 1% of model improvement.
Infrastructure and systems — Turn successful experiments into reusable systems that accelerate future research.
Research direction — Form hypotheses, design convincing experiments, keep up with relevant ML research, and help decide which ideas are worth pursuing.
Whatever the problem needs — Venture into operations, infrastructure, evaluation, data engineering, or other technical side quests when needed to get the research working in practice.

Skills and Qualifications

Requirements

Strong research taste: you can identify important questions, design experiments that answer them, and recognize when a result is real.
Deep enthusiasm for machine learning and a desire to understand models in detail rather than treating them as black boxes.
Strong Python and PyTorch skills, with experience developing and debugging nontrivial ML systems.
Experience working with large, messy datasets and building dependable pipelines or abstractions around them.
Able to iterate quickly while thinking systematically about which work should become durable infrastructure.
Comfortable crossing boundaries between research and engineering and learning unfamiliar tools or domains as needed.
Experience with weather, climate, geospatial data, scientific machine learning, computer vision, or time-series forecasting is helpful, but not required.

Benefits