Top Tech Jobs & Startup Jobs

Own microarchitecture and synthesizable SystemVerilog RTL for a major RDU block from specification through tape-out. Drive datapath pipelining, timing closure, PPA trade-offs, quality gates (lint, CDC, LEC), verification intent, and cross-team integration. Mentor engineers and introduce automation/EDA improvements to meet aggressive frequency targets.

Create technical messaging, demos, collateral, and enablement for AI infrastructure and inference use cases. Translate hardware and architecture details into customer- and field-facing materials, support launches and benchmarking, and partner with product, engineering, sales, and field teams to refine positioning and technical proof points.

Lead end-to-end performance for large-scale LLM inference: build reproducible workload capture and agentic benchmarking, develop performance modeling and simulation, create distributed profiling tooling, guide cross-functional trade-offs, mentor senior engineers, and represent SambaNova to customers and partners to meet SLOs and inform system/hardware planning.

Lead design, development, and optimization of large language models for SambaNova hardware (RDU). Drive hardware-software co-design, define ML strategy, improve training and inference efficiency, mentor senior engineers, and translate advanced ML techniques into scalable, customer-facing solutions across the product lifecycle.

Design and define hyperscale AI compute network architectures. Translate customer and workload needs into scalable, cost‑optimized network and compute product requirements. Lead cross-functional integration, fabric design (InfiniBand/RoCE/Ethernet), lossless Ethernet tuning, high‑speed optics/cabling decisions, lifecycle operations, and deployment strategies for large AI clusters.

Lead development and optimization of the compiler stack to map ML model operations to SambaNova hardware. Collaborate across teams to design, integrate, and deploy compiler features, drive performance debugging, and support productization and customer-facing proposals.

As a Senior AI Systems Performance Engineer, optimize and scale foundation models, enhance performance across various system layers, and deliver high-performance AI applications.

The Principal Engineer will lead post-silicon validation and debugging of high-speed IO and memory subsystems, ensuring performance and reliability for AI compute platforms.

Sell SambaNovas GenAI hardware and software across South East Asia by building territory strategy, generating pipeline, running complex consultative sales cycles, orchestrating cross-functional teams, cultivating C-level relationships, and maintaining accurate CRM forecasting to drive multi-million-dollar deals and regional revenue growth.

Own and develop Cadence-based RTL-to-GDS physical design flows for RDU chips. Maintain and enhance Genus/Innovus/Cerebrus toolflows, script automation (TCL/Perl/Python), collaborate with physical designers and tool vendors, and ensure compliance with advanced TSMC node design rules (3nm and below).