Machine Learning Hardware Engineer

We are building machine learning systems directly on custom hardware and are looking for engineers and researchers who want to help shape the technology from the ground up. This role offers the opportunity to design solutions from first principles, influence research direction, and see your work deployed in highly demanding, performance-critical environments.

Unlike many organizations where hardware, software, and infrastructure are owned by separate teams, we develop the full technology stack in-house. This enables engineers to work across layers, solve bottlenecks directly, and push the boundaries of performance, efficiency, and scalability. We welcome candidates from a variety of technical backgrounds; experience in financial markets is not required.

Key Responsibilities
Design and co-develop machine learning solutions alongside researchers, engineers, and domain experts, treating hardware constraints such as latency, resource utilization, and numerical precision as core design considerations.
Influence the direction of custom hardware platforms by translating machine learning requirements into architectural decisions.
Collaborate closely with hardware engineering teams to implement, validate, and deploy ML inference solutions from research prototypes through production.
Evaluate emerging research in areas such as neural architecture search, machine learning systems, model compression, and quantization, identifying opportunities to improve real-world performance and efficiency.
Drive innovation at the intersection of machine learning and hardware acceleration.

Skills & Experience
Strong understanding of hardware design constraints and trade-offs, including concepts such as pipelining, resource optimization, and fixed-point arithmetic.
Experience working with hardware development technologies such as VHDL, SystemVerilog, HLS tools, or ML-to-hardware frameworks including hls4ml, FINN, or Vitis AI.
Solid foundation in machine learning concepts, including neural network architectures, inference optimization, quantization techniques, and frameworks such as PyTorch or TensorFlow.
Proficiency in Python, C++, or similar languages for simulation, testing, tooling, and development.
Strong communication skills with the ability to collaborate effectively across multidisciplinary teams.

Preferred Qualifications
Experience with ML compiler technologies such as MLIR, TVM, XLA, or similar frameworks used to optimize models for hardware targets.
Background in low-latency, real-time, or resource-constrained systems, including areas such as high-performance computing, signal processing, telecommunications, scientific computing, robotics, or similar domains.
Familiarity with hardware verification methodologies and tools such as SystemVerilog, UVM, or Cocotb.
Advanced degree (MS or PhD) in Electrical Engineering, Computer Science, Physics, Mathematics, or a related discipline, or equivalent industry experience.

Why Join Us
This is an opportunity to work at the intersection of machine learning, hardware architecture, and high-performance systems. You will have the freedom to influence both research and engineering decisions, collaborate with experts across multiple disciplines, and contribute to technology that directly impacts production systems. If you are motivated by solving complex technical challenges and building innovative solutions from the ground up, we would love to hear from you.
Show more Show less