---
title: 'Member of Technical Staff — Inference-Multi-Hardware at RadixArk'
canonical: 'https://feeny.ai/job/member-of-technical-staff-inference-multi-hardware-radixark-palo-alto-5mtbdk97kyhg'
type: 'job'
last_seen: '2026-09-13'
---

# Member of Technical Staff — Inference-Multi-Hardware at RadixArk

- **Company:** RadixArk
- **Location:** Palo Alto, CA
- **Posted:** 2026-08-03
- **Last confirmed live:** 2026-09-13
- **Apply:** https://job-boards.greenhouse.io/radixark/jobs/4343666009

## Job description

## About the Role

RadixArk is seeking a Member of Technical Staff - Inference-Multi-Hardware to push the limits of performance for frontier AI systems.

Most performance engineering assumes a single vendor's stack. This role assumes none. You'll bring up, optimize, and maintain SGLang, Miles, and the RadixArk infrastructure stack across NVIDIA and AMD GPUs, Google TPUs, modern server CPUs, and a growing set of emerging AI accelerators. That means porting kernels and runtimes onto unfamiliar hardware, designing the abstractions that keep one codebase fast on all of it. You will be working directly with silicon and our partners, often on pre-release platforms with immature tooling.

This is one of the broadest technical roles at RadixArk. The problem changes shape with every new platform: a memory hierarchy that punishes your last set of assumptions, a compiler that fuses differently, a collective library that doesn't exist yet. We're looking for engineers who find that appealing rather than exhausting, and who can go deep on a new architecture fast without losing the performance instincts they built on the last one.

## Requirements

- 4+ years of experience in systems, performance, or ML infrastructure engineering
- Deep expertise in at least one accelerator programming model (CUDA, ROCm/HIP, Pallas/XLA, Triton, or a vendor SDK), with demonstrated ability to pick up new ones quickly.
- Strong understanding of accelerator architecture: memory hierarchy, bandwidth limits, occupancy, and the tradeoffs between them
- Experience writing or optimizing high-performance kernels for ML workloads
- Experience with distributed execution and communication libraries (NCCL, RCCL, MPI, or equivalents)
- Proficiency in C++ and Python
- Strong debugging and profiling skills at the system level, including on platforms where the tooling is incomplete or unreliable
- Track record of performance work that shipped into production

Strong Plus

- Experience bringing up ML workloads on new silicon.
- Hands-on depth in more than one vendor ecosystem
- Experience with compiler stacks (XLA, MLIR, TVM, Triton) or building compiler passes and IR transformations
- Experience designing hardware abstraction layers or portable kernel interfaces
- Quantization and mixed-precision work across differing numeric formats and hardware support levels
- Experience with distributed inference systems (SGLang, vLLM) or training/RL frameworks (Miles, Megatron, veRL, TorchTitan)
- CPU inference optimization (AVX-512/AMX, oneDNN, NUMA-aware execution)
- Experience optimizing collective communication at scale, or scaling workloads to 1000+ accelerators
- Contributions to kernel, compiler, or ML systems open source
- Direct collaboration with silicon vendors or cloud partners on technical evaluations
- Background in HPC or other performance-critical systems

## Responsibilities

- Bring up RadixArk's inference and training systems on new accelerator platforms and drive them to competitive performance
- Design hardware abstractions that let a single codebase stay fast across vendors without forking
- Port and optimize kernels across programming models and memory architectures
- Build cross-platform benchmarking, profiling, and regression detection so performance claims hold up on every target
- Debug numerical divergence and correctness gaps between platforms
- Work with vendor engineering teams on pre-release hardware, compiler and driver issues, and roadmap feedback
- Partner with kernel, runtime, distributed systems, and product engineers to land performance wins end to end
- Serve as the internal source of truth on what each platform is actually good at
- Contribute hardware-specific optimizations, benchmarks, and portability work back to open-source SGLang and Miles

## About RadixArk

RadixArk is an infrastructure-first company built by engineers who've shipped production AI systems, created SGLang (30K+ GitHub stars, the fastest open LLM serving engine), and developed Miles (our large-scale RL framework). We're on a mission to democratize frontier-level AI infrastructure by building world-class open systems for inference and training. Our team has optimized kernels serving billions of tokens daily, designed distributed training systems coordinating 10,000+ GPUs, and contributed to infrastructure that powers leading AI companies and research labs. We're backed by well-known infrastructure investors and partner with Nvidia, Google, and frontier AI labs. Join us in building infrastructure that gives real leverage back to the AI community.

## Compensation

Depending on background, skills, and experience, the expected annual salary range for this position is $200,000 - $400,000 USD + equity.

## Equal Opportunity

RadixArk is an Equal Opportunity Employer and is proud to offer equal employment opportunity to everyone regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, and more.

## About RadixArk

## Company Overview
- **One-liner**: RadixArk builds open, large-scale inference and training systems to democratize access to frontier AI infrastructure for the entire AI community.
- **Entity Type**: Private (Seed stage)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2025
- **Founders**: Ying Sheng (CEO) and Banghua Zhu

## Core Business
- **Primary industry/industries**: AI Infrastructure, Deep-Tech, Open Source Software
- **Target customers**: Individual developers, startups, enterprises, and research labs building and deploying AI systems at scale.
- **Mission or purpose statement**: "Make frontier-level AI infrastructure open and accessible to everyone." [radixark.com](https://radixark.com/)

## Products & Services
- **[SGLang (Inference Engine)](https://radixark.com/)**: An open-source, high-performance serving engine for AI models. It has become a de facto standard, powering trillions of tokens daily for leaders like Google, Microsoft, NVIDIA, and xAI. RadixArk is the primary steward. **Type:** Open-Source Software / Managed Service
- **[Miles (RL Framework)](https://radixark.com/blog/radixark-launches-100m-seed)**: An open-source framework for large-scale reinforcement learning and post-training. Designed for efficiency and stability, it has been adopted for large-scale MoE training. **Type:** Open-Source Software
- **Managed Infrastructure & Tooling**: Built on top of SGLang and Miles, RadixArk offers managed services for the full lifecycle of AI development, from training to inference, for teams developing AI at scale. **Type:** Managed Service / Platform

## Market Standing
- **Valuation/Market Cap**: $400 million post-money valuation (as of May 2026) [cbinsights.com](https://www.cbinsights.com/company/radixark)
- **Key Metric**: $100 million total funding (Seed Round)
- **Notable Investors/Partners**: Accel (lead), Spark Capital (co-lead), NVentures (NVIDIA's venture arm), and participation from Google, Microsoft, and other strategic partners. [radixark.com](https://www.radixark.com/blog/radixark-launches-100m-seed)
- **Growth Signals**: The company has 19 employees as of mid-2026 but has seen a monthly headcount growth of +55.6%. Its open-source projects (SGLang and Miles) are already adopted by industry giants and research labs, indicating massive traction and developer mindshare. [linkedin.com](https://www.linkedin.com/company/radixark)

## Competitive Advantages
- **Open-Source Moat**: Its core products, SGLang and Miles, are open-source community standards with deep adoption. This creates a network effect and developer loyalty that is hard for proprietary competitors to replicate.
- **First-Principles Engineering Culture**: The company treats infrastructure engineering as a core creative discipline, not a support function, leading to deeper system-level innovations.
- **Top-Tier Talent & Backing**: Founded by the creators of SGLang and backed by Accel, Spark Capital, and NVIDIA, giving it immediate credibility, capital, and access to frontier hardware.
- **Clear Mission**: Focusing on making infrastructure "10x cheaper and 10x more accessible" directly addresses a massive pain point for the entire AI ecosystem. [radixark.com](https://www.radixark.com/)

## Strategic Focus
- **Growing SGLang & Miles**: Using the $100M seed to accelerate support for new model architectures, hardware platforms, and community improvements.
- **Building Managed Services**: Developing the managed infrastructure and tooling layer on top of its open-source cores to serve a wider range of customers.
- **Hiring Deeply Technical Talent**: Actively recruiting top-tier engineers for kernels, compilers, training systems, and TPU systems to maintain its engineering edge.
- **Expanding Global Reach**: With a Sales role based in Singapore, the company is signaling an intention to serve the APAC market.

## Why Work Here
- **Impactful Mission**: Employees contribute directly to making frontier AI infrastructure a shared foundation, working on problems that affect the entire AI ecosystem.
- **Engineering-Centric Culture**: The company explicitly states that "infrastructure engineering is not a support function," making it an ideal environment for deep-tech systems engineers who want to solve hard, first-principles problems. [radixark.com](https://www.radixark.com/blog/radixark-launches-100m-seed)
- **Work with Open Source at Scale**: You will be contributing to and stewarding widely-used open-source projects (SGLang, Miles) that power trillions of tokens daily.
- **Strong Backing & Early Stage**: Joining a well-funded seed-stage company with a $400M valuation offers significant upside and the chance to shape the company's culture and direction from an early stage.
- **Location & Hybrid Policy**: The company is headquartered in Palo Alto and San Francisco, California, with most roles listed as in-office. They also have a role in Singapore.
- **Notable Perks**: The company's blog emphasizes a culture of being "focused, humble, fearless, and meticulous," which appeals to mission-driven engineers.

## Sources
1. [RadixArk Official Website](https://radixark.com/)
2. [RadixArk Blog: $100M Seed Announcement](https://www.radixark.com/blog/radixark-launches-100m-seed)
3. [RadixArk Jobs on Greenhouse](https://job-boards.greenhouse.io/radixark)
4. [RadixArk LinkedIn Page](https://www.linkedin.com/company/radixark)
5. [CBInsights Company Profile](https://www.cbinsights.com/company/radixark)

## Other roles at RadixArk

- [Talent Operations](https://feeny.ai/job/talent-operations-radixark-palo-alto-bt6t3qbk45qe) — Palo Alto, CA
- [Member of Technical Staff — Developer Experience](https://feeny.ai/job/member-of-technical-staff-developer-experience-radixark-palo-alto-5a7wr087scr0) — Palo Alto, CA
- [Member of Technical Staff — Developer Technology](https://feeny.ai/job/member-of-technical-staff-developer-technology-radixark-palo-alto-vgg40r7f304a) — Palo Alto, CA
- [Product Marketing Manager](https://feeny.ai/job/product-marketing-manager-radixark-palo-alto-jw9xehpywsd4) — Palo Alto, CA
- [Business Development](https://feeny.ai/job/business-development-radixark-palo-alto-c182fj5brh29) — Palo Alto, CA
- [Member of Technical Staff — Performance](https://feeny.ai/job/member-of-technical-staff-performance-radixark-palo-alto-f19h4n3ewdzv) — Palo Alto, CA
- [Member of Technical Staff — Product](https://feeny.ai/job/member-of-technical-staff-product-radixark-palo-alto-as44m8evvp3v) — Palo Alto, CA
- [Technical Program Manager](https://feeny.ai/job/technical-program-manager-radixark-palo-alto-dttqfvsvp6yv) — Palo Alto, CA
- [Member of Technical Staff — Reliability-CI Infrastructure](https://feeny.ai/job/member-of-technical-staff-reliability-ci-infrastructure-radixark-palo-alto-f6br2hsn8yzs) — Palo Alto, CA
- [Member of Technical Staff — Inference-Kernel, Compiler & Communication](https://feeny.ai/job/member-of-technical-staff-inference-kernel-compiler-communication-radixark-palo-jv0nsh2xseay) — Palo Alto, CA