Top Tech Jobs & Startup Jobs

Lead end-to-end technical programs across compiler infrastructure, AI kernel development, GPU runtime, hardware integration, and data center deployments. Break down complex system architecture into milestones, manage cross-team dependencies and suppliers, run planning ceremonies, surface risks, and maintain project documentation and roadmaps to ensure production-ready server solutions.

Lead end-to-end technical programs across compiler, kernel, runtime, hardware integration, and data center deployment. Translate system architectures into schedules, manage cross-team dependencies and suppliers, run planning ceremonies, surface risks, and maintain project documentation and roadmaps to deliver production-ready server solutions.

Lead end-to-end signal and power integrity for high-speed interconnects across architecture, pre-silicon modeling, silicon bring-up, validation, and high-volume manufacturing. Perform channel modeling, EM/field solver correlation to lab measurements, PDN analysis, and SI/PI co-design. Support debug, define design rules with cross-functional teams, lead DVT/PVT to production, and improve internal methodology and tooling.

Own and optimize the end-to-end LLM serving stack on Majestic hardware: port frameworks (vLLM/SGLang), implement batching, scheduling, paged KV cache, distributed inference, multi-modal preprocessing, speculative/prefix decoding, profile and eliminate bottlenecks across runtime, compiler, and hardware.

Lead architecture and end-to-end firmware design for server platforms, including OOB management, power and thermal control, boot sequencing, firmware update pipelines, and firmware security. Collaborate with silicon and hardware teams, drive silicon bring-up, produce architecture/spec documents, and enforce secure firmware practices.

Own and optimize the end-to-end LLM serving stack on Majestic hardware: port and adapt frameworks (vLLM, SGLang), optimize runtime hot paths (batching, scheduler, paged KV cache), implement distributed and multimodal inference, apply inference-time techniques, and profile/benchmark to drive kernel, compiler, and hardware improvements.

Lead architecture and development of complex platform firmware for server System Control Processors, owning end-to-end design, OOB management, power/thermal sequencing, firmware update pipelines, silicon bring-up, and firmware security in collaboration with hardware, silicon, software, and security teams.

Define product strategy and roadmaps for custom AI accelerator platforms and server systems. Translate customer and engineering needs into PRDs and technical specifications, manage schedules and cross-team dependencies, guide product launches, and align stakeholders across silicon, systems, software, and operations.

Lead the AI software stack and compiler platform: define PRDs and roadmaps for compiler toolchains, runtime engines, framework integrations, kernel optimizations, and scale-out orchestration. Coordinate cross-team schedules, partner with framework vendors, and champion developer experience to enable seamless execution on Majestic's Ignite APU.

Lead product definition and delivery for an AI compiler and runtime platform: own compiler/toolchain roadmap, framework integrations (PyTorch, JAX, vLLM, Hugging Face Optimum), kernel optimizations, scale-out orchestration (SLURM, Ray, LMCache), and developer UX to enable optimized execution on Majestic's Ignite APU.