Founding Machine Learning Engineer

The role

You will evaluate and implement machine learning approaches for neural data design problems. You will work with real-time, multi-dimensional, multimodal datasets and collaborate with neuroscience, hardware, and software teams.

What you will do

• Critically evaluate and implement the best machine learning approaches for unique design problems in neural data
• Work with real-time, multi-dimensional, multimodal datasets
• Collaborate closely with neuroscience, hardware, and software teams to co-design end-to-end systems
• Explore new model architectures and perform detailed experimentation and analysis
• Learn neuroimaging and neuroscience context

Required qualifications

• BS or higher in Computer Science, Electrical Engineering, Applied Mathematics, or a related STEM field (exceptional self-taught researchers also considered)
• 3+ years of applied ML research or development experience, or equivalent depth through publications, projects, or startup work
• Strong Python programming skills with experience in PyTorch, TensorFlow, or JAX
• Built and iterated quickly on ML models and pipelines
• Experience with data preprocessing, labeling, and exploratory analysis
• Agility working with multimodal data (e.g., imaging + time series, text + audio)
• Proven ability to thrive in small, fast-moving teams

Nice to have

• Publications in top ML or domain-specific journals/conferences
• Experience with biomedical, neuroimaging, or other high-dimensional sensor data
• A background in signal processing for time-series or imaging data
• Experience with distributed or large-scale training (e.g., mixed precision, very large datasets)
• Knowledge of semi-supervised or self-supervised approaches
• Excitement to learn neuroimaging and neuroscience context

About the company

Orbit is a team of engineers, neuroscientists, and designers solving the challenge of understanding the human brain. They develop a wearable BCI and foundation models of emotion.