below marketmost similar roles pay hereabove market
This role pays less than
86%
of similar roles. Most pay
$174,600–$249,312
— the blue band above.
At the midpoint, this role pays about
$150k
versus about
$212k
for comparable roles.
Based on 240 similar postings.
Employer
About Motorola Solutions
Motorola Solutions, Inc. (NYSE: MSI) is a leading American technology company providing mission-critical communications, video security, and analytics for public safety and enterprise customers.
Motorola Solutions currently has
156 open roles
on FindRole.
Listed pay typically runs
$100,000–$135,000
across 120 roles with salary data.
The Principal Sensor Fusion and Indoor Localization Engineer joins the team to design and optimize algorithms for a next-generation indoor location platform. This role involves transforming noisy real-world RF data into accurate, real-time positioning by architecting AI-driven models for fingerprinting, similarity scoring, and probabilistic grid-cell prediction. You will build path-loss and multipath-aware models while applying signal processing techniques like Kalman smoothing and noise reduction to raw Wi-Fi CSI, BLE RSSI, RTT, and IMU inputs. Key responsibilities include developing hybrid models, running controlled experiments on ground-truth traces, and deploying models into real-time scoring pipelines with sub-100ms inference. Required skills include Python, Matlab, NumPy, SciPy, and scikit-learn, alongside expertise in RF propagation, time-series modeling, and lightweight ML classification for indoor positioning systems.
Architect and develop AI-driven models for indoor localization including fingerprinting and probabilistic grid-cell prediction.
Build and refine path-loss, RF propagation, and multipath-aware models to improve positioning accuracy.
Apply signal processing techniques like filtering and smoothing to transform raw RF and IMU data into high-quality features.
Fuse Wi-Fi RSSI, CSI, BLE RSSI, RTT timestamps, and IMU patterns into hybrid models for real-time positioning.
Evaluate model accuracy using ground-truth traces and tune hyperparameters to improve confidence scoring.
Deploy models into real-time scoring pipelines to ensure sub-100ms inference and large-scale reliability.
Mentor peers in algorithmic reasoning and modeling excellence.
What we're looking for
Master’s degree with 6+ years of professional experience in AI/ML, Electrical Engineering, CS, Applied Math, Robotics, or a related technical discipline.
PhD with 4+ years of professional experience in AI/ML, Electrical Engineering, CS, Applied Math, Robotics, or a related technical discipline (preferred).
Solid understanding of RF propagation, indoor multipath, path-loss modeling, RTT distance estimation, and Channel State Information (CSI) extraction.
Practical knowledge of using subcarrier-level Wi-Fi CSI amplitude and phase metrics to resolve multipath interference and improve positioning resolution.
Experience with filtering, phase unwrapping, Kalman/EMA smoothing, noise modeling, and time-series feature extraction.
Strong Matlab and Python skills (NumPy, SciPy, Pandas, scikit-learn) and experience working with Wi-Fi RSSI, CSI, BLE RSSI, RTT/FTM, and IMU streams.
Hands-on experience with clustering, probabilistic modeling, similarity metrics, and lightweight ML classification/regression.
Experience deploying algorithms to real-time, enterprise-scale systems with tight latency constraints.
C
FreeRTOS
Zephyr
Debian Linux
I2C
SPI
BLE
Firmware
Hardware Validation
Oscilloscope
Logic Analyzer
Distributed Systems
Cloud Services
Mobile
System Bring-up
C++
Python
Deep Learning
CUDA
NVIDIA DRIVE
QNX
RTOS
Sensor Fusion
Perception
ISO 26262
ISO 21448
ASPICE
Simulation
Data Flywheel
Lidar
Radar
Ultrasonics