Embedded AI Engineer
About The Position
Bright Vision Technologies is seeking an Embedded AI Engineer to design, optimize, and deploy machine learning models that run efficiently on resource-constrained edge devices, including mobile platforms, embedded systems, and specialized accelerators. The role calls for expertise in model compression, quantization, and hardware-aware optimization, as well as systems engineering skills to deliver reliable AI capabilities outside the data center. The ideal candidate has shipped edge AI in production environments where compute, memory, energy, and connectivity constraints shape engineering decisions. The position is full-time, direct W2, and 100% remote within the United States. The salary range is $100,000–$150,000 annually. Candidates who are U.S. citizens, Green Card holders, EAD holders, or H-1B transfer candidates are encouraged to apply; the company cannot sponsor new H-1B visa petitions for this position.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
- Six or more years of experience in ML engineering, with significant work on edge or mobile AI.
- Strong proficiency in Python and C++.
- Hands-on experience with model compression, quantization, and pruning techniques.
- Experience with at least one major edge inference framework.
- Solid understanding of mobile and embedded hardware architectures.
- Experience deploying ML models to production on mobile or embedded platforms.
- Strong performance engineering and profiling skills.
- Familiarity with on-device privacy and security considerations.
- Strong communication and cross-functional collaboration skills.
Nice To Haves
- Experience with custom NPU or DSP toolchains.
- Familiarity with federated learning or on-device personalization.
- Exposure to safety-critical or industrial edge deployments.
- Open-source contributions to edge AI frameworks.
- Experience optimizing LLMs for on-device inference.
Responsibilities
- Design and implement edge AI solutions optimized for diverse hardware, including mobile SoCs, NPUs, and embedded accelerators.
- Apply quantization, pruning, distillation, and architectural optimization to fit models within edge constraints.
- Tune model performance for latency, energy efficiency, and memory footprint on target hardware.
- Build cross-platform inference runtimes using frameworks such as TensorFlow Lite, ONNX Runtime, and Core ML.
- Optimize models for accelerator backends including DSPs, NPUs, and mobile GPUs.
- Implement on-device model update, versioning, and rollback workflows for safe staged rollouts and rapid recovery from unexpected model behavior.
- Design hybrid edge-cloud architectures that degrade gracefully based on connectivity and device capability.
- Build telemetry pipelines that respect privacy while enabling continuous improvement.
- Collaborate with hardware, firmware, and product teams to align AI capabilities with device constraints.
- Implement secure execution paths, model protection, and integrity verification on edge devices.
- Develop benchmarking suites to characterize accuracy, latency, and energy trade-offs across devices.
- Drive responsible AI considerations, including on-device privacy and bias evaluation.
- Maintain current technical documentation, including architecture diagrams, design decisions, configuration references, runbooks, and operational procedures.
- Monitor edge AI hardware and software developments, review release notes and community discussions, and translate relevant advances into recommendations and adoption proposals.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
