---
title: 'Member of Technical Staff, TPU Performance Engineering at Inferact'
canonical: 'https://feeny.ai/job/member-of-technical-staff-tpu-performance-engineering-inferact-singapore-hsapg2c1ks2d'
type: 'job'
last_seen: '2026-09-08'
---

# Member of Technical Staff, TPU Performance Engineering at Inferact

- **Company:** Inferact
- **Location:** Singapore
- **Employment:** full-time
- **Work type:** onsite
- **Posted:** 2026-06-26
- **Last confirmed live:** 2026-09-08
- **Apply:** https://jobs.ashbyhq.com/inferact/76d942c3-fbb1-463d-ad79-0d9bfdcc37e9

## Job description

Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, we sit at the intersection of models and hardware, a position that took years to build.

## About the Role

We're looking for a TPU performance engineer to make vLLM a first-class inference engine on Google TPUs. You'll build and optimize TPU backends, compiler integrations, runtime paths, and benchmarking infrastructure using JAX, XLA, Pallas, and related tooling so vLLM can deliver frontier inference performance on TPU hardware.

You'll work at the boundary of inference systems, kernels, compilers, and hardware architecture, improving production-relevant model serving on TPU with clear correctness, latency, and throughput benchmarks. Your work will help make TPU support in vLLM usable, fast, benchmarked, and maintainable.

## Skills and Qualifications

Minimum qualifications:

- Bachelor's degree or equivalent experience in computer science, engineering, systems, machine learning, or similar.
- Hands-on experience building or optimizing TPU workloads using JAX, XLA, Pallas, or related compiler and runtime tooling.
- Deep understanding of TPU execution, memory behavior, compilation, and performance constraints for ML workloads.
- Experience optimizing ML kernels or inference paths such as attention, GEMM, sampling, KV cache, fused kernels, or backend runtime paths.
- Strong performance profiling and benchmarking skills, with the ability to use measurements, compiler artifacts, correctness tests, and reproducible benchmarks to guide optimization work.

Preferred qualifications:

- Experience with vLLM, SGLang, TensorRT-LLM, XLA-based serving, or other LLM inference systems.
- Familiarity with batching, KV cache, decoding, serving tradeoffs, and backend performance constraints in production inference systems.
- Experience with compiler technologies such as XLA, MLIR, LLVM, Pallas, or other kernel DSLs, including lowering, fusion, and backend code generation.
- Knowledge of quantization methods such as INT8, FP8, mixed precision, or TPU-specific numeric formats, including accuracy and performance tradeoffs.

Bonus points if you have:

- Contributed to vLLM, JAX/XLA, Pallas, PyTorch/XLA, compiler projects, or other open-source ML infrastructure.
- Built TPU benchmarking infrastructure or automated performance regression detection for accelerator workloads.
- Worked directly with Google TPU ecosystem stakeholders, accelerator platform teams, or early-access programs to ship backend, compiler, or inference performance improvements.

Logistics

- Location: This role is based in Singapore.
- Compensation: Depending on background, skills, and experience, the expected annual salary range for this position is S$200,000 to S$400,000 annually + equity.
- Visa sponsorship: We sponsor visas on a case-by-case basis.
- Benefits: Inferact offers a generous benefits package, including medical, dental, and vision coverage.

## About Inferact

## Company Overview
- **One-liner**: Inferact is a startup founded by the creators of vLLM, the leading open-source LLM inference engine, dedicated to making AI inference cheaper and faster at global scale.
- **Entity Type**: Private (Seed stage; raised $150M in seed funding)
- **Headquarters**: San Francisco, California, United States (with a second office in Singapore)
- **Founded**: 2025
- **Founders**: Simon Mo (CEO), Woosuk Kwon, Kaichao You (Chief Scientist), Roger Wang, Joseph Gonzalez, Ion Stoica

## Core Business
- **Primary industry**: AI infrastructure / open-source inference engine for large language models
- **Target customers**: AI labs, hyperscalers, startups, and enterprises deploying large-scale AI models (B2B, primarily technical teams)
- **Mission**: Grow vLLM as the world’s AI inference engine and accelerate AI progress by making inference cheaper and faster.

## Products & Services
- **vLLM (Open-Source Inference Engine)**: The core product – an open-source LLM inference engine that supports 500+ model architectures and runs on 200+ accelerator types. Inferact stewards and supercharges vLLM, with all optimizations flowing back to the community.
- **Managed Inference Infrastructure (in development)**: Inferact is building infrastructure to absorb the complexity of deploying frontier models at scale, aiming to make it as simple as spinning up a serverless database.

## Market Standing
- **Valuation/Market Cap**: Not disclosed (private company)
- **Key Metric**: Total funding of $150M (seed round, announced 2026)
- **Notable Investors/Partners**: Lightspeed Venture Partners (lead), Redpoint Ventures, Andreessen Horowitz, Altimeter Capital, Sequoia Capital, The House Fund, GC&H Investments, and others. Partnerships include NVIDIA, Red Hat, DigitalOcean, and Cohere.
- **Growth Signals**: 
  - $150M seed round – one of the largest seed rounds in AI infrastructure.
  - 22 employees with +27.3% monthly headcount growth.
  - vLLM ecosystem: 2,000+ contributors, 500+ model architectures, 200+ accelerator types.
  - Day-zero support for new model architectures (e.g., Cohere’s Command A+) and hardware integrations.
  - Active hiring with 5 open positions across inference, performance, kernel engineering, and cloud orchestration.

## Competitive Advantages
- **Deep ecosystem moat**: vLLM is the de facto standard open-source inference engine, with a massive community and integrations across models and hardware that took years to build.
- **Founding team credibility**: Creators and core maintainers of vLLM, with experience deploying at frontier scale (research and production).
- **Hardware-software co-optimization**: Positioned at the intersection of model innovation and hardware diversity, enabling day-zero compatibility and performance optimizations.
- **Open-source commitment**: All improvements flow back to vLLM, ensuring community trust and rapid adoption.

## Strategic Focus
- **Current priorities**: Push vLLM performance further, deepen support for emerging model architectures (MoE, multimodal, agentic), expand hardware coverage (200+ accelerators), and build managed infrastructure to simplify deployment.
- **Growth direction**: Close the capability gap between models and serving systems; absorb complexity so teams can focus on innovation rather than infrastructure.

## Why Work Here
- **Culture**: High-caliber engineering team with roots in vLLM, PyTorch, and top AI labs. Emphasis on open-source contribution and cutting-edge inference research.
- **Work policy**: Hybrid with a San Francisco HQ; at least one open role (Member of Technical Staff, Exceptional Generalist) is listed as Remote.
- **Notable perks**: Opportunity to work at the frontier of AI inference, directly impact the open-source ecosystem, and collaborate with partners like NVIDIA, Red Hat, and major AI labs.
- **Engineering culture**: Strong focus on systems engineering, kernel optimization, and cloud orchestration – ideal for engineers passionate about performance and infrastructure.

## Sources
1. [inferact.ai](https://inferact.ai/)
2. [LinkedIn](https://www.linkedin.com/company/inferact)
3. [CB Insights](https://www.cbinsights.com/company/inferact)
4. [Sequoia Capital](https://sequoiacap.com/companies/inferact/)
5. [Ashby Jobs](https://jobs.ashbyhq.com/inferact)

## Other roles at Inferact

- [Member of Technical Staff, Inference](https://feeny.ai/job/member-of-technical-staff-inference-inferact-remote-ezb6x9bq2fty)
- [Member of Technical Staff, Cloud Orchestration (Remote)](https://feeny.ai/job/member-of-technical-staff-cloud-orchestration-remote-inferact-remote-pzza0bak1bw7)
- [Member of Technical Staff, Cluster Administration](https://feeny.ai/job/member-of-technical-staff-cluster-administration-inferact-san-francisco-hzy2pmhsv4ca) — San Francisco, CA
- [Member of Technical Staff, Site Reliability Engineer](https://feeny.ai/job/member-of-technical-staff-site-reliability-engineer-inferact-san-francisco-4hdd72zebn0b) — San Francisco, CA
- [Founding Product Designer](https://feeny.ai/job/founding-product-designer-inferact-san-francisco-8fhyc666jrb6) — San Francisco, CA
- [Head of Engineering](https://feeny.ai/job/head-of-engineering-inferact-san-francisco-rhcv5bpns37j) — San Francisco, CA
- [Product Marketing Manager](https://feeny.ai/job/product-marketing-manager-inferact-san-francisco-ap07axndjdjb) — San Francisco, CA
- [Member of Technical Staff, AMD GPU Performance Engineering](https://feeny.ai/job/member-of-technical-staff-amd-gpu-performance-engineering-inferact-san-francisco-q425hfnsdrh2) — San Francisco, CA
- [Member of Technical Staff, AMD GPU Performance Engineering](https://feeny.ai/job/member-of-technical-staff-amd-gpu-performance-engineering-inferact-singapore-q7jn24nd0rbf) — Singapore
- [Member of Technical Staff, Performance and Scale](https://feeny.ai/job/member-of-technical-staff-performance-and-scale-inferact-singapore-vyavkymh08h3) — Singapore