Software Platform Architect
Saaki, Argus & Averil Consulting (company site, opens in a new tab)15–20 yrsBengaluruOn-siteDirect career pageEst. 40–70 LPA
Posted 16h ago
Reach people at Saaki, Argus & Averil Consulting
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Saaki, Argus & Averil Consulting you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Lead end-to-end software platform architecture for next-generation AI accelerators covering runtime scheduler, memory manager, drivers, compiler backend, and ML framework integration.
- Drive hardware-software co-design to optimize accelerator performance including memory usage, MIMD scheduling, and HBM access in collaboration with silicon teams.
- Oversee software bring-up, integration with major ML frameworks (PyTorch, vLLM, DeepSpeed), SDK CI/CD automation, release management, and mentor engineering teams (5-10 engineers).
Minimum Requirements
- 15-20 years experience in software architecture for HPC, GPU, NPU, or many-core AI accelerator platforms.
- B.Tech/M.Tech or M.S./Ph.D. in Computer Science, Electrical Engineering, or related field.
- Proven ownership of production software stack from silicon bring-up to deployment across compiler backend, runtime, drivers, and ML framework integration.
- Strong C/C++ systems programming and Python scripting skills; hands-on with CUDA, HIP, OpenCL, MPI, and OpenMP.
Ideal Candidate Profile
- Technical leader with deep expertise in hardware-software co-design and heterogeneous workload porting for AI accelerators.
- Experienced in managing complex software ecosystems integrating compiler backends, runtime, and ML frameworks for specialized accelerator hardware.
- Capable of driving cross-functional collaboration between software, silicon, firmware, security teams, and external partners in high-complexity environments.