We are augmenting our Boston/San Jose offices by hiring a Staff Engineer AI/ML – Edge Compute to join a new initiative that may be of strong interest to your students, colleagues, and collaborators working in non-traditional AI compute, neuromorphic engineering,
edge AI.
We are building a pioneering organization focused on advancing the frontiers of Edge AI compute and intelligent sensors. We are seeking a Staff level AI/ML Lead – Edge Compute who will play a critical role in benchmarking and developing new state-of-the-art
AI models and advanced optimization techniques to enable foundation models and Tiny ML to run efficiently on edge platforms. You will collaborate with startups and internal teams to optimize and compile cutting-edge AI models for custom hardware compute.
-
Benchmark and develop new state-of-the-art uAI and foundation models specifically tailored for edge devices.
-
Research, introduce, and implement advanced optimization techniques to run large and complex AI models efficiently on analog compute, Neuromorphic, and heterogeneous compute
-
Collaborate closely with startups, internal engineering teams, and hardware partners to optimize and compile AI models for edge compute architectures and custom accelerators.
-
Validate, adapt, and fine-tune models to meet defined KPIs such as latency, power consumption, accuracy, and throughput.
-
Evaluate and recommend appropriate SDKs, toolchains, compilers, and runtime environments to maximize hardware and software performance.
-
Contribute to the technical roadmap and guide best practices for scalable and robust Edge AI deployment.
-
Mentor and guide junior team members and collaborate across multi-disciplinary teams to deliver production-ready solutions.
-
Master’s or PhD in Computer Science, Electrical Engineering, Machine Learning, or a related field.
-
7+ years of experience in AI/ML development, with a strong focus on deploying models on edge or embedded devices.
-
Deep expertise in AI model optimization techniques (e.g., quantization, pruning, knowledge distillation) and familiarity with transformer-based foundation models.
-
Strong hands-on experience with frameworks such as TensorFlow, PyTorch, ONNX, TVM, or similar toolchains for model compilation and acceleration.
-
Knowledge with SNN frameworks Brian2, NEST, BindsNET – advantage
-
Solid understanding of heterogeneous compute architectures (CPUs, GPUs, NPUs, FPGAs) and experience working with custom hardware or ASICs is highly desirable.
-
Proven track record of cross-functional collaboration with hardware, software, and product teams, as well as external partners or startups.
-
Excellent problem-solving skills, with a practical mindset to balance performance, efficiency, and production readiness.
-
Strong communication skills and ability to thrive in an innovative, fast-paced environment.