Machine Learning Engineer

THE COMPANY

Silvus Technologies, a leading provider of advanced MANET and MIMO communications systems, is reshaping mesh network technology for mission-critical applications – on the ground, in the air and  battle‑proven Stream Caster family of MANET radios and proprietary MN‑MIMO waveform provides the vital communications link for defense, law enforcement and public safety agencies around the world, and in the toughest operational environments.

With deep roots in DARPA research, Silvus Technologies develops world‑class advanced communications technologies that are reshaping the tactical communications landscape. From pure line‑of‑sight to extreme non‑line‑of‑sight, Silvus radios form a self‑healing, self‑forming mesh network, enabling secure and reliable connectivity, including video and high‑bandwidth data.

Silvus Technologies is a wholly owned subsidiary of Motorola Solutions, Inc.

Would you like to join an incredibly talented group of people, doing very challenging work, with the prime directive of "
Keeping Our Heroes Connected
"?

Silvus is seeking a Machine Learning Engineer who will report to the R&D Director, Machine Learning on the R&D team. The successful individual in this role will focus on applying machine learning and data‑driven techniques to improve the performance, efficiency, and adaptability of Silvus’ advanced MIMO radios and wireless networking systems. This individual will work closely with experts in wireless communications, DSP, networking, and embedded systems to develop ML‑driven features that solve real‑world problems in dynamic and challenging RF environments.

This position is based at Silvus Technologies’ headquarters in the heart of vibrant West Los Angeles, CA
, and is on a hybrid schedule. A minimum of 3 days onsite per week is expected. On‑site days are Mondays, Wednesdays, and Thursdays.

The following is a list of at least some of the current essential job functions of the position. Management may assign or reassign duties and responsibilities at any time at its discretion.

• Research, design, and implement machine learning algorithms to enhance performance in wireless communication systems (e.g., link adaptation, interference mitigation, anomaly detection, spectrum sensing).
• Analyze real‑world RF datasets to extract insights and develop predictive models.
• Develop software prototypes and integrate ML algorithms with Silvus’ radio firmware and networking stack.
• Collaborate with cross‑functional teams to define ML use cases and evaluate the impact of deployed models.
• Contribute to the design of data pipelines and infrastructure for training, testing, and validating models.
• Participate in performance benchmarking and iterative improvement cycles.
• Stay current with the latest Machine Learning research for wireless and embedded systems.
• Perform other related duties of which the above are representative.

• Bachelor of Science degree in Electrical Engineering, Computer Science, Computer Engineering, or related field plus a minimum of 2 years of experience in machine learning, with demonstrated application to real‑world problems; no experience required with an advanced degree (MS or PhD).
• Strong foundation in supervised and unsupervised learning and statistical modeling.
• Experience with Python ML frameworks (e.g., Tensor Flow, PyTorch, scikit‑learn, etc.).
• Exposure to MATLAB or C/C++ for signal processing algorithm development.
• Must be a U.S. Citizen due to clients under U.S. government contracts.
• All employment is contingent upon the successful clearance of a background check and drug test.

• MS or Ph.D. in Electrical Engineering, Computer Science, or a related field.
• Demonstrated experience with RF signal classification, anomaly detection, or spectrum monitoring.
• Proficiency in MATLAB or C/C++ for signal processing algorithm development.
• Familiarity with wireless communication concepts (e.g., PHY/MAC layers, MIMO, OFDM, spectrum access).
• Familiarity with embedded ML, real‑time systems, or deploying ML on edge devices.
• Background in adaptive modulation, beamforming, or cognitive radio…