Member of Technical Staff, ML Systems — Confidential AI Infrastructure Startup

Aionia Group; Menlo Park (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Aionia Group in Menlo Park, CA is hiring a Member of Technical Staff, ML Systems to accelerate model training and inference across image, video, and world-model workloads. You will work with a founding team on kernels, runtimes, and distributed engines that power production-scale ML stacks.

You’ll optimize GPU performance, profile bottlenecks with Nsight, and implement low-level CUDA and Triton improvements.

Qualifications

• Worked on inference or training performance — GPU kernels, runtime, or distributed execution.
• Optimized diffusion, video, image, or other multimodal model workloads.
• Degree in Computer Science or a related quantitative field.

Responsibilities

• Optimize GPU and system performance for training and inference across image, video, and world-model workloads.
• Profile and remove bottlenecks at the kernel, memory, system, and cluster level using Nsight and related tooling.
• Write low-level optimizations in CUDA and Triton on code paths that run in production.
• Build distributed inference and training engines for diffusion models across multiple GPUs and nodes.
• Own communication performance — NCCL, RDMA over InfiniBand or RoCE, and disaggregated serving.
• Build benchmarking and regression harnesses so performance gains don't slide back in production.

Skills

GPU kernel optimization

Distributed systems

Profiling

Performance optimization

Multimodal models

Education

Bachelor's degree in Computer Science or related field

Tools

CUDA

Triton

PyTorch

Nsight

NCCL

RDMA / InfiniBand

Job description

GPU & ML Systems · Below the Application Layer

Member of Technical Staff, ML Systems
Make the model 10x faster.

About the Company

A deep-tech AI infrastructure startup rebuilding the training and inference stack for world models. Today's ML infrastructure was built for language models — this team is rebuilding it for video, image, and world-model workloads, co-designing across three layers at once: low-level GPU kernel optimization, distributed systems, and the algorithms and models themselves.

The company came out of stealth with public benchmarks already in hand: a leading open video-generation model running roughly 10x faster at half the cost on its stack, a 2K image-generation model running in about four seconds for three cents, and a real-time video model running faster than real time. The founding team — with prior experience across leading AI labs, hyperscalers, and infrastructure companies — works out of Menlo Park in person and has an API already in production. The company raised a $10M seed round and is approaching a Series A.

"You report to the CEO. He runs every screen himself and makes the hiring decision — there is no layer between the work and the person who decides. The work sits below the application layer: kernels, runtimes, and distributed engines for video and world models. Nothing here is agents or RAG."

The Opportunity

You’ll own speed and efficiency across the full ML systems stack — low-level kernels, distributed inference engines, and multi-node training and serving systems for image, video, and world-model workloads. You’ll work directly alongside a founding team that between them covers distributed systems, kernel optimization, cloud infrastructure, and research.

You’ll feel at home here if you’d rather make a video model ten times faster than train one.

What You’ll Do

• Optimize GPU and system performance for training and inference across image, video, and world-model workloads
• Profile and remove bottlenecks at the kernel, memory, system, and cluster level using Nsight and related tooling
• Write low-level optimizations in CUDA and Triton on code paths that run in production
• Build distributed inference and training engines for diffusion models across multiple GPUs and nodes
• Own communication performance — NCCL, RDMA over InfiniBand or RoCE, and disaggregated serving
• Build benchmarking and regression harnesses so performance gains don't slide back in production

Requirements

• Worked on inference or training performance — GPU kernels, runtime, or distributed execution
• Optimized diffusion, video, image, or other multimodal model workloads
• Degree in Computer Science or a related quantitative field

Baseline

• 1+ years of experience in deep learning inference or training systems, or distributed systems
• Built inside or contributed to an inference engine or runtime — vLLM, SGLang, TensorRT-LLM, or equivalent

CUDA Triton PyTorch Nsight Systems / Compute NCCL RDMA (InfiniBand / RoCE)

Interview Process

1

30-minute conversation with the CEO on background, motivation, and a first read on GPU/distributed systems depth.

2

Domain Deep Dive

60-minute technical round with a member of the founding team on kernels, inference, or distributed execution.

3

System Design

60-minute systems design session with a member of the founding team.

4

Optional Onsite

If not already done in person, a chance to meet the full team on-site in Menlo Park.