Machine Learning Research, RF Foundation Models Specialist

The role

You will formulate new ML problems in RF sensing and spectrum understanding. You will design experiments, build models for signal environments, and optimize models for deployment constraints.

What you will do

• Formulate new ML problems in RF sensing and spectrum understanding
• Design experiments and evaluation approaches that reflect real operating conditions
• Build models for structured, noisy, and partially observed signal environments
• Improve robustness across propagation, interference, and low-visibility waveform conditions
• Optimize models for throughput, latency, and deployment constraints
• Move promising research into a release path for real systems
• Use field performance to inform the next generation of models and tooling

Required qualifications

• Deep mathematical and modeling fundamentals
• Strong hands-on experience with modern ML frameworks and experimental practice
• Ability to work in domains where problem formulation is as important as implementation
• Strong instincts for signal-rich, structured, non-generic data
• Comfort operating with ambiguity and changing requirements
• Clear technical communication and cross-functional collaboration

Nice to have

• Background in RF or signal-centric ML (spectrum sensing, modulation recognition, or related work)
• Experience building for constrained inference (quantization, kernel-level optimizations, or similar)
• Evidence of research impact: publications, open-source implementations, or prior work building new architectures that shipped

Benefits

• Above-market salary, equity, and benefits package
• Early Series A Equity
• Excellent health, dental, and vision coverage
• 401(k) match - up to 4% of your salary
• Flexible PTO
• Daily office lunches in NYC

Before you apply

• To conform to U.S. Government technology export regulations, including the International Traffic in Arms Regulations (ITAR) you must be a U.S. citizen, lawful permanent resident of the U.S., protected

About the company

DS creates systems that power the next generation of radio spectrum intelligence. They collect radio data, train neural networks to decipher it, and run them on small chips.