Sr. Sensor Software Engineer (Edge Sensing, Real-Time Signal Processing & Systems)

SafePointe® is an AI-based concealed weapons detection system built for high-throughput, free-flow screening. We are hiring a Sr. Software Engineer to own the sensor data path end-to-end: edge acquisition, time synchronization, signal processing, data-quality instrumentation, and reliable delivery of sensor features to downstream detection and fusion services. A near-term priority is improving measurement fidelity and time-detail preservation while maintaining noise rejection and robust operation in real-world, high-interference environments—closely partnering with hardware on the signal-chain and ADC capture roadmap.

Essential Responsibilities/Duties

Own the sensor software pipeline from raw capture → preprocessing → feature generation → model-facing interfaces, with clear quality metrics, acceptance criteria, and versioned releases.
Build and optimize real-time signal processing (filtering, decimation/oversampling strategy, de-noising, interference rejection, event detection) while balancing latency, group delay, and CPU/GPU load on edge devices.
Implement robust timing and alignment across sensors and cameras (timestamping, clock discipline, buffering, synchronization, and alignment checks) to support sensor fusion and ground-truth labeling workflows.
Own our edge stack on NVIDIA Jetson Orin (Ubuntu/Linux): service orchestration (systemd), configuration management, performance tuning, and reliability hardening for 24/7 deployments.
Develop and maintain production data transport and messaging (e.g., ZMQ-based pipelines), including backpressure handling, fault tolerance, and deterministic behavior under load.
Integrate with operational infrastructure: AWS IoT Greengrass deployments/updates, device health reporting, and observability (Prometheus metrics, structured logs, on-device diagnostics).
Build test and characterization tooling: reproducible playback harnesses, synthetic/recorded datasets, regression tests, and automated reports to prevent early decisions based on incomplete or biased signals.
Partner with hardware and manufacturing to support calibration, traceability, factory test integration, and field failure analysis; translate bench measurements into actionable software changes and clear corrective actions.

Minimum Qualifications

B.S. in Computer Science, Electrical/Computer Engineering (or related) or equivalent practical experience.
6+ years building production software for sensor/edge systems, real-time pipelines, or high-throughput time-series processing.
Strong fundamentals in signal processing and time-series systems (sampling/decimation, filtering concepts, spectral analysis/PSD, noise/interference mitigation).
Proficiency in Python for analysis, test automation, and production services; plus strong experience in a systems language (C++ preferred; Rust/Go acceptable depending on stack).
Experience on embedded Linux / edge compute: debugging, profiling, performance optimization, and reliable service operation.
Proven ownership mindset: translating ambiguous requirements into measurable specs, shipping iteratively, and maintaining quality through CI, regression tests, and operational telemetry.

Preferred Qualifications

Experience with NVIDIA Jetson/embedded GPU stacks (CUDA/TensorRT or GPU acceleration for signal processing and/or inference).
Familiarity with Stereolabs ZED (or comparable) camera SDKs and time synchronization between vision and non-vision sensors.
Experience with AWS IoT Greengrass (or comparable edge deployment frameworks), OTA update strategies, and device fleet operations.
Experience designing observability for edge systems (Prometheus, alerting, structured logs, remote debugging workflows).
Experience with manufacturing/field test systems: calibration routines, factory automation, traceability, and reliability analysis.
Comfort collaborating across hardware, ML, and operations—especially in environments with RF/EMI interference, variable site conditions, and strict uptime requirements.

Tools & Methods (Representative)

Edge compute: NVIDIA Jetson Orin (Ubuntu/Linux), systemd services, performance profiling and thermal/power-aware tuning.
Data pipeline: Python services, ZMQ messaging, time-series buffering/alignment, deterministic failure handling.
Ops: AWS IoT Greengrass, device configuration + OTA updates, Prometheus metrics, structured logging, incident-ready diagnostics.
Process: design reviews, DVT-style validation, clear specs + test reports, version-controlled datasets and reproducible experiments.

Travel: 15%

Hybrid Workplace

SoundThinking follows a hybrid schedule for employees who live equal to or less than 50 miles from one of our office locations, which include Fremont, CA, Tucson, AZ, Washington, D.C., Orlando, Florida, or Iselin, NJ. Employees are expected to work onsite for a minimum of 3 days per week, unless the advertised role has a specific on-site requirement. The specific days for in-office are dependent on the office location.

Note: The Company reserves exclusive right in its sole discretion to modify, adjust, delete, add or otherwise change the above at any time.

SoundThinking provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, national origin, age, disability or genetics. In addition to federal law requirements, SoundThinking complies with applicable state and local laws governing nondiscrimination in employment in every location in which the company has facilities. This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation and training.

SoundThinking expressly prohibits any form of workplace harassment based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status. Improper interference with the ability of SoundThinking’s employees to perform their job duties may result in discipline up to and including discharge. If you are an individual with a disability and require a reasonable accommodation to complete any part of the application process, or are limited in the ability or unable to access or use this online application process and need an alternative method for applying, you may contact SoundThinking at careers@soundthinking.com for assistance.

#LI-SSD

Apply for this job

First name

Last name

Email address

Location

Phone number

Resume

Attach resume

Attach another file

Attach file

How did you learn about this job?

Referred by?

Are you legally authorized to work in the United States? Please answer yes or no.

Will you now or in the future require sponsorship for employment visa status? (H-1B. F-1B, CPT, OPT, etc.). Please answer yes or no

Ability to work onsite at SoundThinking's Fremont, CA office location on Tuesdays, Wednesdays, and Thursdays?

We invite you to complete the optional self-identification questions below used for compliance with government regulations and record-keeping guidelines. Any self-identification information provided will not be considered in the selection process.

GENDER

VETERAN STATUS Learn more about veteran statuses

If you believe you belong to any of the categories of protected veterans listed below, please indicate by selecting the appropriate category(ies). The hiring employer is subject to the Vietnam Era Veterans' Readjustment Assistance Act of 1974, as amended by the Jobs for Veterans Act of 2002, 38 U.S.C. 4212 (VEVRAA) and requests this information in order to measure the effectiveness of the outreach and positive recruitment efforts it undertakes pursuant to VEVRAA.

DISABILITY STATUS Learn more about disability statuses

We are required by law to provide equal employment opportunity to qualified people with disabilities. We are also required to measure our progress toward having at least 7% of our workforce be individuals with disabilities. To do this, we must ask applicants and employees if they have a disability or have ever had a disability. Because a person may become disabled at any time, we ask all of our employees to update their information at least every five years.

Identifying yourself as an individual with a disability is voluntary, and we hope that you will choose to do so. Your answer will be maintained confidentially and not be seen by selecting officials or anyone else involved in making personnel decisions. Completing the form will not negatively impact you in any way, regardless of whether you have self-identified in the past. For more information about this form or the equal employment obligations of federal contractors under Section 503 of the Rehabilitation Act, visit the U.S. Department of Labor’s Office of Federal Contract Compliance Programs (OFCCP) website at www.dol.gov/ofccp.