TPU Inference Performance Engineer

Job Description

Inferact is seeking a TPU performance engineer to enhance vLLM's performance on Google TPUs. You will build and optimize backends, while ensuring benchmarks for correctness and efficiency.

We're looking for candidates with a strong background in computer science, hands-on TPU optimization experience, and familiarity with JAX and XLA. The role is based in Singapore, and offers a competitive salary range of S$200,000 to S$400,000 annually, plus a generous benefits package.

#J-18808-Ljbffr

Apply Now

Similar Opportunities

nexadept

Singapore / Global
TPU Performance Engineer
nexadept

Singapore / Global
LLM Inference Performance Engineer
Adaption

Singapore / Global
Inference Performance Engineer
inferact

Singapore / Global
Member of Technical Staff, TPU Performance Engineering
Inferact

Singapore / Global
Member of Technical Staff, TPU Performance Engineering
Google India

Singapore / Global
Senior ML Engineer - TPU Training & Inference Optimizer

View all jobs

Name	Expiration	Description
ATTBCookie* ATTBUserID ATTB_LinkedUserID	2 years 400 days 1 year	These cookies are used to remember a user’s choice about cookies on thebigjobsite.com. Where users have previously indicated a preference, that user’s preference will be stored in these cookies.
ATTBTracking*	Session	These cookies are used by ATTB to understand user interaction with the website.
last-search search redirect-stage original-keyword	1 day Session 1 hour 1 hour	These cookies are used by thebigjobsite.com to pass search data between our own pages.
datadome	1 year	DataDome is a cybersecurity solution to detect bot activity
jja*	1 days	Used to track if you have seen the Job Alerts prompt and hold settings for your profile. Job Alerts is a service you can subscribe to to receive information about new jobs.

Name	Expiration	Description
_ga _gid _gat_gtag_* _ga_JH3TWMTYRK __gads	Typically ranges from session-based (24 hours) to longer-lasting cookies (up to 2 years).	Google Analytics Cookies: Used for tracking and analytics, these cookies collect information about website usage to help understand user behavior. Visitor tracking, session management, and ad performance analysis.
_gcl_au NID DV UULE, EUULE	Typically lasts from a few days to months.	Google Ads / AdSense Cookies: Cookies used for advertisement personalization, conversion tracking, and remarketing by Google Ads. Track ad clicks and impressions, personalize ad content, and measure conversions.
_uetsid _uetvid	Typically lasts from a few days to months.	Microsoft Advertising (Bing Ads): Microsoft's tracking cookies for advertising and user analytics. Track user sessions and unique visitors for remarketing campaigns.
SID SSID SAPISID, APISID SIDCC SOCS AEC	Typically lasts from a few days to months.	Google Account/Authentication Cookies: These cookies are set by Google services (e.g., Gmail, YouTube) to manage user sessions, preferences, and account security. Authentication, session security, and maintaining user preferences.
__secure*	Typically lasts from a few days to months.	Secure Cookies (Potentially Third-Party): Cookies prefixed with __secure* are often used for enhanced security in user sessions or tracking. These are typically first- or third-party cookies, depending on their origin.
MSPTC MUID SRCHD SRCHHPGUSR SRCHUID SRCHUSR USRLOC WLS _EDGE_S _EDGE_V _SS _U ANON	Typically lasts from a few days to months.	These cookies form part of an analytics service that connects data from Bing with actions performed on the website. These cookies allow Bing to serve relevant advertisements to visitors across the Microsoft Bing network
_clck _clsk CLID ANONCHK MR MUID SM	Typically lasts from a few days to months.	Microsoft Clarity: is a cutting-edge behavioral analytics tool that helps us understand user interaction with your website. By using Clarity, we can enhance the user experience.

Start Your Search Here

Cookie Settings

Cookie Settings

Inferact

TPU Inference Performance Engineer

Job Description

Success! You're now signed up for Job Alerts.

Similar Opportunities

nexadept

TPU Performance Engineer

nexadept

LLM Inference Performance Engineer

Adaption

Inference Performance Engineer

inferact

Member of Technical Staff, TPU Performance Engineering

Inferact

Member of Technical Staff, TPU Performance Engineering

Google India

Senior ML Engineer - TPU Training & Inference Optimizer