Role
Port and optimize a containerized video analytics pipeline to run on CPU-constrained router hardware (Cradlepoint OS, Wi-Fi 7 PrplOS, FWA routers). You'll own the full stack: model optimization, container architecture, and on-device inference performance.
---
What You'll Do
- Port GPU-based video analytics models (object detection, classification) to CPU-only router targets
- Optimize inference pipeline to stay under 100MB memory footprint using SLMs
- Build containerized architecture with dynamic cloud-driven model loading
- Tune accuracy/performance tradeoffs on ARM/MIPS router hardware
- Integrate with Cradlepoint OS and PrplOS environments
- Benchmark and iterate on detection accuracy vs. latency on constrained hardware
---
Required
- 4+ years in embedded systems or edge ML deployment
- Experience with containerization (Docker, LXC) on constrained devices
- ML model optimization: quantization, pruning, ONNX, TensorFlow Lite, OpenVINO
- Video analytics / computer vision (YOLO variants, object detection pipelines)
- Python + C/C++ on Linux embedded targets
- Cross-compilation, profiling, and memory optimization
---
Strong Plus
- Cradlepoint NetCloud / PrplOS / OpenWRT experience
- NPU/DSP acceleration on router-class SoCs
- DeepStream or similar inference pipeline experience (GPU→CPU migration)
- SLM deployment (sub-1B parameter models on edge)
- RTSP/video streaming on embedded Linux
---
You Are
- Comfortable with no GPU — CPU-only inference is the constraint, not a fallback
- Pragmatic about accuracy tradeoffs at the edge
- Experienced navigating vendor OS lock-in and limited debugging toolchains
About Cognizant’s IoT Practice:
Intelligent, IoT-enabled products will soon result in the proliferation of data and disrupt virtually all industries. To be successful, both large and small companies must leverage IoT capabilities by designing modern products that fundamentally connect people with processes. Within Cognizant IOT, we engineer industry-aligned, IoT-enabled products that merge industry needs with human drivers. Our intelligent products will revolutionize experiences and result in exciting, transformative outcomes. Without human-centered thinking, connected products are just standalone things—but with it, our modern connected products facilitate a unified way of life enjoyed by all.
*Please note, this role is not able to offer visa transfer or sponsorship now or in the future*
- Applications will be accepted until Sep 30, 2026
- LI#- #LI-SC6
Compensation & Benefits
$95,000– $118,000 per year + Cost of Living Allowance
Bonus + Comprehensive Benefits
Additional Information
- Onsite role
- ⚠️ Visa sponsorship is not available now or in the future. Candidates requiring sponsorship will not be considered.
Benefits: Cognizant offers the following benefits for this position, subject to applicable eligibility requirements:
• Medical/Dental/Vision/Life Insurance
• Paid holidays plus Paid Time Off
• 401(k) plan and contributions
• Long-term/Short-term Disability
• Paid Parental Leave
• Employee Stock Purchase Plan
About Cognizant
Cognizant (Nasdaq: CTSH) is an AI Builder and technology services provider, bridging the gap between AI investment and enterprise value by building full-stack AI solutions for our clients. Our deep industry, process and engineering expertise enables us to build an organization’s unique context into technology systems that amplify human potential, drive tangible outcomes and keep global enterprises ahead in a fast-changing world. See how at cognizant.ai or @cognizant.
Additional employment information
Compensation information is accurate as of the date of this posting. Cognizant reserves the right to modify this information at any time, subject to applicable law.
Applicants may be required to attend interviews in person or by video conference. In addition, candidates may be required to present their current state or government issued ID during each interview.
Cognizant is an equal opportunity employer. Your application and candidacy will not be considered based on race, color, sex, religion, creed, sexual orientation, gender identity, national origin, disability, genetic information, pregnancy, veteran status or any other characteristic protected by federal, provincial or local laws.
