Jobs at SambaNova Systems

Leads company-wide IT infrastructure, end-user technology, security operations, and DevOps support. Responsibilities include managing on-premises and cloud systems, networks, storage, identity, laptops, SaaS tools, help desk operations, onboarding, access controls, monitoring, incident response, CI/CD tooling, automation, vendors, budgets, and team growth. The role combines strategic leadership with hands-on systems configuration, troubleshooting, and automation.

Train and evaluate machine learning models that improve large language model inference efficiency and capability. Responsibilities include speculative decoding, quantization, sparsity, distillation, pruning, parameter-efficient fine-tuning, agentic systems, benchmarking, research implementation, and reinforcement learning or post-training. The role collaborates with performance, compiler, runtime, and product teams to ship model improvements.

Develop and optimize compiler infrastructure for SambaNova’s RDU AI accelerator. Responsibilities include implementing IR passes, lowering and partitioning machine learning models, tensor tiling, on-chip memory management, fabric mapping, and low-level debugging in C++ and Python. The role collaborates with runtime and hardware teams and includes mentorship while building production compiler software.

Build and operate the machine learning inference stack for SambaNova’s RDU accelerators. Develop production Python features including speculative and constrained decoding, tool calling, prompt caching, long-context inference, and vLLM integration. Maintain public inference APIs, create accuracy and regression tests, and troubleshoot latency, throughput, and reliability issues. The role requires strong systems and programming fundamentals, experience with LLM serving frameworks and inference techniques, and PyTorch knowledge.

Build and maintain cloud and on-premises infrastructure supporting SambaNova’s AI inference platform. Responsibilities include managing Kubernetes clusters, Terraform and Ansible automation, monitoring and dashboards, CI/CD pipelines, regional infrastructure deployment, capacity support, and incident response. The role also participates in an on-call rotation and requires programming or scripting, cloud, networking, Linux, containerization, infrastructure-as-code, and monitoring experience.

Develop runtime software across kernel drivers, user-space libraries, networking, and system tools for SambaNova AI hardware. Build and test features on large multi-node systems, diagnose performance bottlenecks, and collaborate with hardware and compiler teams. The role requires C, C++, Rust, Python, Linux systems programming, high-speed networking, distributed communication libraries, and debugging experience.

Lead development and optimization of the compiler stack for ML systems, collaborate across teams, integrate and deploy products, map ML operations to hardware, and drive compiler infrastructure innovation and performance debugging.

Brings up and optimizes foundation models on SambaNova’s AI platform. Profiles performance across compiler, runtime, and hardware layers; identifies bottlenecks; applies quantization, kernel fusion, scheduling, and memory optimizations; benchmarks inference throughput and latency; and collaborates with machine learning, compiler, runtime, and hardware teams to deliver product improvements.

Own full-lifecycle recruiting for go-to-market and product roles across Sales, Marketing, Customer Success, and Product. Partner with hiring managers to define roles, build sourcing strategies, calibrate pipelines, design interviews, manage feedback, and close passive talent. Maintain accurate recruiting data and metrics in Greenhouse while influencing senior leaders and using AI to improve recruiting workflows. This is a six-month contract with potential extension or conversion.

Own and operate a global AI inferencing platform: ensure uptime, low-latency performance, scalability and cost efficiency. Build monitoring, alerting, CI/CD, IaC, autoscaling, capacity planning, incident response, and participate in a shared on-call rotation to maintain 24/7 service reliability.

Design and implement RTL components for AI accelerator ASICs from microarchitecture through tape-out and silicon bring-up. Responsibilities include writing and debugging SystemVerilog, optimizing power, performance, and area, supporting synthesis and timing closure, and applying lint, CDC, LEC, and assertion-based quality checks. The engineer collaborates with architecture, verification, and physical design teams while contributing to compute datapath, on-chip network, and memory subsystems.

Own microarchitecture and synthesizable SystemVerilog RTL for major AI accelerator blocks from specification through tape-out. Drive power, performance, and area optimization, timing closure, synthesis, STA, lint, CDC, LEC, assertions, and verification collaboration. Partner with architecture and software teams on performance improvements, advance EDA automation, lead design reviews, and mentor engineers.

Design and implement block- and SoC-level DFT architectures for complex AI accelerator chips. Develop ATPG, MBIST, scan, JTAG, IEEE 1500, and IJTAG infrastructure; automate insertion, pattern generation, coverage analysis, and debug; support DFT timing closure, ATE deployment, silicon bring-up, diagnosis, failure localization, yield analysis, and manufacturing test optimization.

As a Senior Cloud SRE, you'll ensure the reliability and performance of our AI inferencing service, handle incident management, and optimize cloud infrastructure and resource utilization.

Design and own RTL hardware blocks for AI accelerator ASICs through microarchitecture, implementation, tapeout, and silicon bring-up. Develop high-performance SystemVerilog designs, meet power, performance, and area targets, and collaborate with verification and physical design teams. Implement assertions and run lint, CDC, LEC, synthesis, and timing flows. Support design reviews, post-silicon debugging, and improvements to ASIC design methodologies, including AI and automation in EDA workflows.

Define and own networking architecture for next-generation super-pod ML hardware. Lead R&D, specify high-performance networking fabrics, drive ML networking roadmap, collaborate cross-functionally across silicon, systems, and software, contribute to industry standards, and deliver performant, reliable, and secure interconnect solutions at scale.

Build and scale SambaNova’s analyst relations program across semiconductors, AI infrastructure, cloud, data centers, and enterprise technology. Develop analyst relationships, lead briefings and research engagements, prepare executives and technical experts, translate complex technology into credible narratives, track program impact, and incorporate analyst insights into product strategy, positioning, go-to-market planning, and executive decisions.

Embed with enterprise customers to design, build, and deploy production generative AI applications on SambaNova hardware and SambaStack. Architect LLM workflows (RAG, agents, fine-tuning), optimize inference performance, troubleshoot across model/software/hardware layers, translate field needs to product teams, support technical sales and POCs, develop reusable reference architectures, and present results to customers and internal stakeholders.

Serve as the primary post-sales partner for enterprise accounts, leading onboarding, adoption monitoring, mitigation of churn risk, and expansion. Build tailored success plans, coordinate cross-functional delivery, deliver executive business reviews, drive upsell/cross-sell, and relay customer feedback to Product and Engineering.