Back
Tier-1 employer, Bangalore location, and mid-level seniority create high competition.
Specialized ML compiler and accelerator performance skills reduce transferability across industries.
Mandatory 5+ years and specific ML compiler/performance expertise enforce strict shortlisting.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Drive continuous improvement of the ML software/hardware stack for Google first-party teams and Google Cloud Platform customers.
Develop deep understanding and perform performance debugging across ML frameworks (JAX, PyTorch), XLA, and runtime stack to enhance efficiency of ML workloads.
Collaborate with teams owning ML stack components and contribute to OSS ML inference frameworks to identify and solve performance bottlenecks, including support for new ML paradigms like scaling TPU chips.
Bachelor's degree or equivalent practical experience.
5 years of software development experience in C++ or Python.
Experience in machine learning infrastructure development or ML performance engineering.
Preferred experience includes ML compilers, compiler optimizations, accelerator hardware (TPUs/GPUs), ML inference frameworks (vLLM, SG Lang, Pathways), and ML frameworks (TensorFlow, JAX, PyTorch, Keras).
Proven expertise in ML infrastructure with hands-on experience in performance optimization and debugging across ML frameworks and runtime stacks.
Experienced in working with compiler internals and hardware accelerators related to ML workloads.
Able to collaborate cross-functionally to drive performance improvements and support cutting-edge ML paradigms in a large-scale production environment.