Software Reliability Engineer - LPU Hardware DataFlow

Jelentkezés a cégnél

Cég neve

NVIDIA Hungary Kft.
Munkavégzés helye

Távmunka / Remote

Munkaidő, foglalkoztatás jellege
- Teljes munkaidő
- Általános munkarend
Elvárt technológiák
- HARDWARE TESTING C++ JAVA LINUX PYTHON HARDWARE– TEST AUTOMATION CI REGRESSION TESTING DEBUGGING TEST MANAGEMENT
Biztosított eszközök
- Linux
Elvárások
- Angol középfok
- 5-10 év tapasztalat
- Főiskola

Állás elmentve

A hirdetést eltávolítottuk a mentett állásai közül.

Responsibilities

Develop and conduct reliability and qualification campaigns for NVIDIA hardware (accelerators, boards)
Build and sustain automated test frameworks for driver stability and regression
Lead efforts to improve hardware and driver reliability to meet customer expectations
Complete and automate hardware stress tests, longevity and environmental tests, and failure analysis
Take responsibility for driver reliability testing – stability under load, regression suites, compatibility matrices, and crash/hang triage
Fix logic bugs before they even happen by providing formal correctness proofs
Develop and sustain driver reliability test frameworks: automated stability evaluations, regression test suites, and compatibility assessments across OS, driver versions, and hardware SKUs
Diagnose and identify driver and hardware failures: investigate crashes, freezes, and errors; collaborate with driver and hardware groups to resolve problems and enhance test coverage
Establish and track reliability metrics and SLOs for hardware and drivers; perform post-mortems and encourage advancements in test automation and coverage
Build, implement, and run hardware reliability and qualification tests: stress tests, longevity tests, thermal/power cycling, and environmental tests on GPUs and accelerators
Automate test running, result gathering, and reporting; incorporate reliability tests into CI and release workflows; manage lab or farm infrastructure for reliability testing across EMEA and worldwide

Requirements

BS or higher degree or equivalent experience with 8+ years in reliability engineering, hardware testing, driver testing, or SRE with a focus on hardware/drivers
Functional programming experience (haskell, nix)
Strong System level programming experience (C++, Rust, Java)
Strong experience with Linux and scripting (Python, Shell) for test automation, result parsing, and tooling
Proficiency in building automated test pipelines; experience with CI/CD and with running tests at scale (e.g. test farms, lab automation)
Ability to prioritize failures, examine logs and dumps, and collaborate with driver or hardware teams to identify root causes of issues
Strong communication skills in English; capable of collaborating with distributed teams across EMEA and worldwide

Nice-to-have

Experience with GPU or accelerator reliability testing; familiarity with NVIDIA or other GPU/driver ecosystems, Experience with hardware durability or certification testing (stress, longevity, thermal, power) and/or driver consistency and regression testing, Background in driver development, kernel debugging, or low-level software; ability to read driver code and correlate behavior with test failures, Experience with hardware testing tools, lab automation, or DUT (device-under-test) management at scale, Knowledge of reliability standards and methods (e.g. FIT rates, accelerated life testing, failure analysis), Experience with firmware or BIOS reliability testing; understanding of hardware–software interaction and error reporting (e.g. AER, MCE)

What we offer

Full time position
Remote work options in Netherlands, UK, Hungary

Company info

NVIDIA is the world leader in accelerated computing. NVIDIA pioneered accelerated computing to tackle challenges no one else can solve. Our work in AI and digital twins is transforming the world's largest industries and profoundly impacting society.