Performance & Debug Software Engineer - AI Inference
Positron AI · United States · Just now · 0 applicants
NewRemoteFull-timeSenior
Pay
$200k–$300kListed
Workplace
Remote
Job type
Full-time
Level
Senior
Source: jobright · Posted by joined-scrapper
About the role
Positron AI seeks a Senior Performance & Debug Software Engineer to profile and optimize end-to-end large language model inference on custom AI accelerators. The role focuses on building distributed inference and KV cache capabilities, creating benchmarks, and debugging across application, runtime, driver, firmware, and hardware boundaries.
What you’ll do
Profile and optimize the inference stack
Develop distributed inference and KV cache capabilities
Build benchmarks and regression tests
Influence hardware and software architecture
Debug across application, runtime, driver, firmware, and hardware boundaries
Analyze performance optimizations in customer production deployments
What you’ll need
Strong C++ and Python skills, with hands-on experience profiling complex systems exercising Linux VFIO interfaces
Deep understanding of memory hierarchy, concurrency, data movement, batching, scheduling, and performance measurement
Hands-on experience with profilers, counters, traces, and statistical methods to distinguish signal from noise
Ability to debug across application, runtime, driver, firmware, and hardware boundaries
Experience bringing up software on new silicon and analyzing performance optimizations in production deployments
Enthusiasm for AI-accelerated development, including using coding agents and orchestrating subagents
Original job description
Positron AI is hiring a Performance & Debug Software Engineer to improve end-to-end large language model inference performance on its custom AI accelerators. The role focuses on profiling and optimizing the inference stack, developing distributed inference and KV cache capabilities, building benchmarks and regression tests, and influencing hardware and…