ML Systems Engineer — Inference Acceleration

Arago Inc.; Paris; On-site; EUR 110,000 - 170,000; Full time

Benefits offered by this job

Stock options

Health insurance

Pension contributions

Professional development

Job summary

Arago Inc. in Paris is seeking a senior ML inference engineer to optimize execution on a custom accelerator. You will work across kernels, model execution, and multi-device distribution to maximize performance and efficiency.

You will contribute to the software stack, with emphasis on CUDA/Triton-based kernels, operator fusion, and advanced inference-serving techniques; strong C++/Python skills and English proficiency are required.

Qualifications

• Strong experience in high-performance ML inference.
• Deep understanding of computer architecture and memory hierarchies.
• Experience developing and optimizing custom kernels (CUDA/Triton/ROCm).
• Experience with operator fusion, tiling, scheduling and data movement optimization.
• Experience with distributed model execution and parallelism.
• Hands-on with modern inference-serving systems (e.g., KV-cache, continuous batching).
• Strong C++ and Python skills; exposure to MLIR is a plus.
• English proficiency.

Responsibilities

• Analyze modern AI workloads to identify bottlenecks on Arago's accelerator.
• Develop and optimize custom kernels and execution strategies to maximize device utilization.
• Map models and operators across multiple Arago devices with efficient communication.
• Develop inference-serving techniques like continuous batching and KV caches.
• Build profiling and performance-analysis tools for kernels, models, and serving workloads.
• Collaborate with hardware, compiler, and runtime teams to influence future features.

Skills

ML inference

GPU/accelerator

Kernel optimization

Distributed execution

Inference-serving

C++

Python

English

Job description

Meet Arago and the Aragonians

Arago's mission is to reengineer the foundations of computing from first principles.

The explosive growth of AI is pushing the industry to rethink how processors are built. Arago is meeting that challenge with a proprietary technology that fuses optical and CMOS technologies to deliver an order-of-magnitude increase in performance.

Arago is the fastest, and currently the only, company to have built such a processor. It's backed by leading deep-tech investors and some of the most respected figures in semiconductors and computing, including the CEO of Arm, the founder of macOS who worked directly with Steve Jobs at Apple, an Nvidia Fellow, the Head of Optics at Google, and many other industry leaders.

Our work is guided by three clear values: do great things, move with high velocity, and operate as one unit. We work in a demanding environment where constant learning, ownership, and execution are expected, and where exceptional people have the opportunity to do their life’s work.

What you'll do

Optimize the execution and serving of modern AI models on Arago's custom accelerator. Work across kernels, model execution, multi-device distribution, runtime, and inference serving, while helping shape the software stack around the capabilities of Arago's hardware.

Required Skills and Experience

• Strong experience in high-performance ML inference, GPU/accelerator programming, or ML systems engineering.

• Deep understanding of computer architecture, accelerator/GPU execution models, memory hierarchies, parallelism, and performance bottlenecks.

• Experience developing and optimizing custom kernels using CUDA, Triton, ROCm/HIP, or equivalent low-level programming environments.

• Experience with operator fusion, tiling, scheduling, data movement optimization, graph execution, and profiling of compute- and memory-bound workloads.

• Strong understanding of distributed model execution, including tensor, pipeline, sequence, and/or expert parallelism and communication/computation overlap.

• Hands-on experience with modern inference-serving systems such as vLLM, SGLang, TensorRT-LLM, or equivalent, including KV-cache management, continuous batching, paged attention, and prefill/decode scheduling.

• Strong C++ and Python skills, and comfort working on a custom accelerator stack where compiler, runtime, kernels, and abstractions are actively being developed. Exposure to or experience with MLIR and MLIR dialects is a strong plus.

• Language: English at a proficient level.

Responsibilities

• Analyze modern AI workloads and identify kernel-, runtime-, memory-, and system-level bottlenecks on Arago's accelerator.

• Develop and optimize custom kernels, fused operators, and execution strategies to maximize device utilization.

• Design efficient mappings of models and operators across multiple Arago devices, including communication and synchronization strategies.

• Develop inference-serving techniques such as continuous batching, paged KV caches, prefix/context caching, chunked prefill, and prefill/decode interleaving or disaggregation.

• Build profiling, benchmarking, and performance-analysis infrastructure spanning kernels, full models, and serving workloads.

• Work closely with Arago's hardware, compiler, and runtime teams to co-design software abstractions and influence future hardware features based on real model workloads.

Pay and benefits

• Competitive cash compensation, with final package based on location, experience, and the pay of team members in similar positions.

• Meaningful stock option plan offered (included in the majority of full time offers).

• Healthcare coverage (including family-friendly options), pension contributions, professional development support, and 25 days of PTO, in addition to public holidays.

• Ownership of a key technical domain, with significant vertical and/or horizontal growth opportunities, based on performance and individual drive.

We look forward to hearing how you can help shape the future of AI at Arago.