Hardware ML Architect for Custom AI Accelerators

IMC Trading; Chicago (IL); On-site; USD 200,000 - 225,000; Full time

Benefits offered by this job

Discretionary bonus

Paid leave

Insurance benefits

Job summary

A global trading firm is seeking an engineer to architect machine learning solutions on custom hardware in Chicago. The role involves defining ML models, collaborating with traders and engineers, and evaluating research for improvements. Candidates should have a strong understanding of hardware constraints, experience with VHDL/SystemVerilog, and proficiency in Python or C++. An advanced degree in a related field is preferred. This position offers a salary range of $200,000 - $225,000 and includes bonus opportunities and benefits.

Qualifications

• Solid understanding of how ML models can be efficiently mapped onto hardware.
• Experience with ML frameworks such as PyTorch/TensorFlow.
• Ability to work collaboratively across disciplines.

Responsibilities

• Architect and co-design ML models with traders and engineers.
• Shape custom hardware roadmap based on ML model requirements.
• Work with hardware engineers to implement and verify solutions.
• Evaluate research for measurable improvements in systems.

Skills

Understanding of hardware constraints and design trade‑offs

Experience with VHDL/SystemVerilog development

Understanding of machine learning fundamentals

Proficiency in Python, C++, or similar languages

Strong communication skills

Education

Advanced degree (MS or PhD) in EE, CS, Physics, or related field

Tools

hls4ml

FINN

Vitis AI

Job description

We are deploying machine learning directly onto custom hardware – and we want you to help drive it from the ground up. This is an initiative where you'll have the rare opportunity to architect solutions from scratch, influence technical research direction, and see your work drive real impact in one of the most demanding computing environments in the world.

We build the hardware, the software, and the infrastructure, so when you hit a bottleneck, you can fix it - there's no vendor to wait on and no abstraction layer you're not allowed to touch. If you've ever wanted to push the boundaries of what's computationally possible, this role is for you. We're looking for researchers and experienced engineers from any background. Trading experience is a bonus, not a prerequisite.

Your Core Responsibilities

• Architect and co-design ML models with traders, quant researchers, and software engineers, treating hardware constraints (latency budgets, resource limits, numerical precision) as first-class design inputs
• Shape our custom hardware roadmap by translating ML model requirements into concrete architectural decisions
• Work hands-on with hardware engineers to implement, verify, and deploy ML inference solutions from proof-of-concept through production
• Track and evaluate emerging research in neural architecture search, machine learning systems and quantization methods, and determine what translates to measurable improvements in our systems
  
  

Your Skills And Experience

• Solid understanding of hardware constraints and design trade-offs (e.g., pipelining, resource utilization, fixed-point arithmetic) that shape how ML models can be efficiently mapped onto FPGAs or custom ASICs
• Experience with hardware fundamentals, whether through VHDL/SystemVerilog development, HLS tools, or ML-to-hardware frameworks like hls4ml, FINN, or Vitis AI
• Understanding of machine learning fundamentals – neural network architectures, inference optimization, quantization techniques, ML frameworks such as PyTorch/TensorFlow
• Proficiency in Python, C++, or similar languages for tooling, testing, and simulation
• Strong communication skills and ability to work collaboratively across disciplines with both technical and non-technical teams
  
  

Nice to Have

• Exposure to ML compiler infrastructure such as MLIR, TVM, XLA, or similar tools for lowering and optimizing models for hardware targets
• Background in latency-sensitive or resource-constrained systems including high-frequency trading, particle physics data acquisition, real-time signal processing, or similar domains
• Familiarity with functional verification methodologies (for example SystemVerilog, UVM, Cocotb)
• Advanced degree (MS or PhD) in EE, CS, Physics, or related field, or equivalent depth through industry or research experience
  
  

The Base Salary range for the role is included below. Base salary is only one component of total compensation; all full-time, permanent positions are eligible for a discretionary bonus and benefits, including paid leave and insurance. Please visit Benefits - US | IMC Trading for more comprehensive information.

Salary Range

$200,000 - $225,000 USD

About Us

IMC is a global trading firm powered by a cutting-edge research environment and a world-class technology backbone. Since 1989, we’ve been a stabilizing force in financial markets, providing essential liquidity upon which market participants depend. Across our offices in the US, Europe, Asia Pacific, and India, our talented quant researchers, engineers, traders, and business operations professionals are united by our uniquely collaborative, high-performance culture, and our commitment to giving back. From entering dynamic new markets to embracing disruptive technologies, and from developing an innovative research environment to diversifying our trading strategies, we dare to continuously innovate and collaborate to succeed.