Back
Niche senior AI systems architect in Bangalore reduces candidate density.
Highly specialized ML systems and compiler expertise limits cross-industry transferability.
12+ years plus specific LLM, compiler, and runtime expertise enforces strict filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Lead design and ownership of application/framework layer and deployment stack for Next Generation Accelerator AI platform.
Architect integration of AI model frameworks (vLLM, PyTorch, TensorFlow, JAX/XLA) into the platform ensuring performance, correctness, and scalability.
Own end-to-end model execution behavior, deployment workflows, and drive performance optimizations across model, framework, and runtime layers.
12+ years of work experience in AI/ML systems or software architecture.
Strong experience with PyTorch, Transformers, and large language models (LLMs).
Hands-on experience with LLM deployment and scalable inference engines such as vLLM, Triton, or SGLang.
Expertise in system design, APIs, and cross-layer integration for AI platforms.
Experienced in building scalable AI platforms for cloud or edge environments with a focus on deployment and runtime optimization.
Demonstrated ability to work cross-functionally with compiler, runtime, and low-level software teams to deliver integrated AI solutions.
Deep technical knowledge of LLM serving systems and AI accelerators (GPUs, NPUs) alongside familiarity with compiler frameworks like XLA or MLIR.