FuriosaAI

You'll own developer-facing documentation for FuriosaAI's SDK and LLM inference stack. You'll translate complex systems into clear tutorials, API references, and guides, while building automated pipelines that **validate documentation against live hardware**. This is a docs-as-code role that **reads source code** and runs the stack on real accelerators.

You'll lead **AI system PCB design** for a **cutting-edge hardware team**. Capture schematics and consult on PCB layout and SI/PI. You'll work with **hybrid flexibility** at the Seoul HQ.

You'll explore cutting-edge AI trends like **LLM**, **Agentic AI**, and **Diffusion** to integrate into NPU systems. You'll lead research for **top-tier conference publications** and collaborate with leading global institutions.

You'll **design High-Speed Interface Controller IP** and perform **performance analysis** in IP/chiptop level simulation. Your work ensures **silicon debug and validation**.

You'll lead **Korea media strategy** and translate **deep-tech innovations** into compelling stories for FuriosaAI. Your core impact is establishing FuriosaAI's global presence and credibility through strong technical thought leadership.

You'll be the **architect of our US talent engine**, driving the first waves of hiring that will define our presence in the US market. You'll navigate a **hyper-growth, fast-moving environment** where the playbook is not yet written. This is your chance to be a **pivotal player in building our US cross-functional team**.

You'll **design and execute workplace experiences** for a **global AI semiconductor company**, building office management standards and processes from scratch. You'll **own facility management and operations** to support rapid organizational growth.

You'll **build investor relationships** and **market intelligence capabilities** for a leading AI semiconductor company. Your insights will inform strategic positioning as the company scales toward IPO.

You'll **support Furiosa's capital strategy and commercialization** by developing innovative financing structures for customers and partners. Your work will enable FuriosaAI's technology to reach customers at scale **while supporting fundraising and strategic initiatives**. This role offers the opportunity to help build one of the world's leading AI semiconductor companies **as it scales toward IPO and beyond**.

You'll join FuriosaAI's Finance team to support financial health and rapid growth through accounting, settlement, and ERP system enhancement. You'll manage expense reviews, month-end closing, and internal reporting while improving financial processes. **This role offers hands-on experience in diverse finance operations** for both domestic and international entities.

You'll lead and expand strategic partnerships across the semiconductor and AI infrastructure ecosystem, building relationships with foundries, ASIC providers, IP vendors, and EDA companies. Your core impact will be strengthening supply chain resilience and accelerating product execution through **deep ecosystem engagement**. You'll act as a key external representative with **senior executives** and drive cross-functional alignment to position the company as a **trusted partner** across the global silicon ecosystem.

You'll lead **semiconductor ecosystem partnerships** to strengthen **supply chain resilience** and **accelerate product execution**. You'll work with foundries, ASIC providers, IP vendors, and advanced packaging partners to drive strategic initiatives.

You'll drive **global talent acquisition** for FuriosaAI, partnering with hiring managers to scale the organization. You'll execute **data-driven hiring strategies** and build a pipeline of world-class technical talent. This role offers the chance to shape **employer branding** in the competitive AI and semiconductor markets.

You'll bring up first silicon and validate core IPs for an AI accelerator. You will ensure reliability and mass-producibility while providing customer technical support.

You'll apply **software engineering** to improve **reliability and scalability** of production infrastructure and customer-facing services at FuriosaAI. You'll work across baremetal Kubernetes clusters, cloud control planes, networking, and observability systems. Your mission is to drive improvements through code, automation, and architectural changes.

You'll enable customer AI applications on **FuriosaAI NPUs** and optimize inference code using **Furiosa SDK**. As a trusted technical advisor, you'll solve customer issues and drive adoption. This role offers a chance to work with cutting-edge AI hardware and influence product direction.

You'll **integrate and verify HSI IP blocks** in SoC, supporting physical implementation and performance analysis. You'll **configure IP blocks for maximum performance** and collaborate with vendors on silicon testing and debugging.

You'll manage global payroll, benefits, and HR operations for multiple countries, ensuring compliance and optimizing processes. You'll collaborate with Korean HQ and global branches to align policies and support employee inquiries. The role offers a chance to build scalable people operations from the ground up.

You'll bridge FuriosaAI's software stack and market demand by developing a high-impact AI application ecosystem. You'll lead **model enablement** and build **end-to-end reference applications** like RAG and agentic systems. Collaborate with the global developer community through open-source channels.

You'll develop and maintain **ROM code** and early boot software for high-performance AI semiconductors. You will port **Arm Trusted Firmware** and implement system trust primitives like Secure Boot and firmware update. Collaborate with hardware teams for SoC bring-up and low-level debugging.

You'll define **architecture and microarchitecture specifications** for AI accelerators. You'll implement designs in **RTL (System Verilog)** and iterate for optimal power, timing, and area. This role offers the chance to shape next-generation **machine learning hardware**.

You'll design **intermediate representations** and **abstraction boundaries** for FuriosaAI's deep learning compiler, enabling high-performance AI systems. Your work will ensure correctness and scalability across the full compilation stack.

You'll **integrate and verify IP blocks** in SoC for a leading AI semiconductor company and support physical implementation. Your work will define SoC-level specifications and architecture. This role offers the chance to work on **high-speed connectivity IP** and **memory subsystems**.

You'll **define and implement verification strategies** for cutting-edge semiconductor designs at FuriosaAI. Your work will drive **functional and code coverage closure** while collaborating with cross-functional teams. You'll also **architect verification infrastructure** and deploy UVM-based methodologies.

You'll serve as a **technical bridge** between customers and internal engineering teams, providing support for **AI processors** and **Linux/PCIe systems**. You'll resolve technical issues, execute product testing, and lead training to ensure customer success.

You'll develop **model compression tools** for FuriosaAI's NPU, enabling customers to maximize inference efficiency. You'll ensure **quantized models** are production-ready and advance compression algorithms. This role combines **software engineering** with deep learning optimization.

You'll define and implement verification plans, build test benches, and drive closure on design quality. You'll collaborate with cross-functional teams to ensure **highest design quality** in block/IP/SoC verification. Debug and resolve **functional failures** while working with Design, Model, Emulation, and Silicon validation teams.

You'll evaluate the PPA of our design as part of chip architecture planning. You'll perform synthesis, logic equivalence checking, SDC & UPF development, and static timing analysis. This role collaborates closely with a design house to achieve the best outcomes.

You'll develop **NPU Management Interface firmware** that controls communication between hosts and NPU devices. Your work enables **out-of-band management, monitoring, and control** for next-generation AI accelerators. You'll ensure compliance with industry specifications like **MCTP and PLDM**.

You'll lead **technical content creation** for **AI hardware and software products**, translating complex innovations into engaging stories for developers and enterprises. Your work will shape Furiosa's **global technical voice** and drive community engagement.

You'll design and improve **CI systems** and **developer workflow tooling** to maximize compiler team productivity. You'll optimize large-scale test execution across clusters for model performance. This role focuses on building **stable, efficient, and self-healing CI orchestration** systems.

You'll design and develop core infrastructure for an **Agent System Framework**, including agent orchestration and context management. You'll collaborate across teams to prototype and scale **new agent capabilities** into production. This role focuses on building **developer-facing interfaces** like CLI and SDK.

You'll develop and maintain Linux PCIe device drivers and kernel modules, optimizing **PCIe subsystem behavior** including DMA, IOMMU, interrupts, and BAR mapping. You'll build **user-space libraries and APIs** for high-performance data paths, working closely with hardware/firmware teams to build end-to-end PCIe I/O pipelines.

You'll establish **company-wide security standards** based on **Zero Trust principles** and design secure infrastructure. You'll lead **security architecture across cloud and SaaS environments**.

You'll design the integration layer and runtime environments for **PyTorch-native kernel execution**, enabling custom kernels to run as native extensions. You'll develop **high-level tensor programming models** and implement virtual ISAs for direct hardware control. This role sits at the intersection of AI frameworks and systems programming.

You'll translate complex AI hardware and software innovations into clear, engaging content for developers and researchers. You'll **collaborate with engineering teams** to write technical blog posts and tutorials that amplify Furiosa's mission. This role shapes the company's **technical voice globally**.

You'll manage projects delivering **card-level and server-level AI solutions** in collaboration with internal teams and **global manufacturing partners**. Your work will balance technical and business needs to enable **groundbreaking AI hardware** reaching the market.

You'll design and execute workplace experiences for a global AI semiconductor company. Your role will define and refine office management standards and processes. You'll lead **facility management**, **operations planning**, and **vendor coordination** to support rapid organizational growth.

You'll lead APAC marketing initiatives for an AI inference infrastructure company. You'll partner with product, engineering, sales, and global marketing to localize global strategies and drive region-specific execution. This role is based at our Korea HQ, where you'll shape how Furiosa is understood across Korea, Japan, and Southeast Asia.

You'll **design and develop end-to-end security architecture** for SoC-based products including **secure boot, anti-rollback, and key provisioning**. You'll integrate and optimize **hardware cryptographic engines** and perform vulnerability analysis to harden system-level protection.

You'll design and implement the **low-level runtime stack** that drives FuriosaAI's NPU hardware, from device driver interfaces to embedded firmware. Your work will **maximize inference throughput** and minimize latency for real-world AI workloads. This role offers the chance to **optimize across the full stack** — from firmware to user-space — on cutting-edge accelerator hardware.

You'll define **SI/PI requirements** and perform simulations at electromagnetic, circuit, and system levels for **chiplet and 3D-IC technologies**. Your work will guide design decisions on stack-up, routing, and PDN architecture, ensuring robust system-level performance. You'll also collaborate with **cross-functional teams** to correlate simulations with measurements.

You'll drive the seamless transition of AI accelerator cards from development to **global mass production**, bridging R&D and external manufacturing. You'll be the cornerstone of our hardware delivery, ensuring **material readiness** and managing build schedules. This role offers a chance to define the **foundational supply chain** for cutting-edge AI hardware.

You'll support product strategy and market research for AI infrastructure and enterprise technology, helping organize customer feedback and create internal documentation. This role offers exposure to ecosystem mapping, launch readiness, and cross-functional product planning.

You'll operate at the intersection of product planning, technical program management, and go-to-market functions. You'll help shape market segments, use cases, and product adoption strategies. This role offers exposure to **full-stack AI** and **ecosystem development** at a fast-growing AI chip company.

You'll define and operationalize AI-assisted engineering workflows for the compiler team, identifying high-leverage bottlenecks and shipping repeatable tooling. You'll be the first person in this newly created role, with scope spanning development, code review, debugging, and CI/testing. **No playbook exists yet**—you'll map the undefined space yourself.

You'll develop end-to-end architectures for **enterprise AI solutions** using **FuriosaAI's Tensor Contraction Processor** and serve as a trusted advisor to customers in the APAC region. You'll lead pre-sales activities and **drive customer adoption** of cutting-edge AI accelerator technologies.

You'll develop **hardware-aware compiler optimizations** for high-performance AI systems. You'll build **analytical performance models** to drive data-driven optimization. This role combines program analysis with algorithmic problem-solving.

You'll design and implement the front-end pipeline for **FuriosaAI's compiler**, translating models from frameworks like PyTorch into internal IR. You'll develop **graph-level optimizations** and evolve a tensor-level kernel language. This role is central to building **high-performance AI systems**.

You'll manage external manufacturing partners for data center server systems with GPU/NPU accelerators, overseeing the full lifecycle from NPI to mass production. Your core impact will be driving **production execution**, quality control, and delivery across OEM/ODM partners. This role offers the chance to work on cutting-edge **AI hardware** in a dynamic environment.

You'll build and operate stable test infrastructure for AI semiconductor and system development, collaborating with HW/SW teams to manage servers, network, and data center environments. Your core impact is maximizing development productivity and system reliability through efficient infrastructure management.

You'll be the primary technical authority for **AI/LLM model deployments** on FuriosaAI's RNGD chips, owning end-to-end customer enablement. You will run POCs, benchmarks, and debugging sessions directly in **customer environments**. This role offers the chance to shape **next-generation AI infrastructure** at a cutting-edge semiconductor startup.

You'll perform **silicon bring-up** and **functional validation** of key IPs such as CPU, DRAM, PMU, and NAND. Your work ensures **mass production yield** through margin evaluation and stability testing. You'll collaborate with QA teams to secure screen criteria and support solution development.

You'll develop **autonomous agent systems** that solve complex engineering problems using **Agentic AI**. Your focus is building self-improving systems that learn from execution results. Join a team creating new AI-driven workflows for engineering challenges.

You'll manage **monthly consolidations** and **financial statements** for global entities, ensuring compliance and accuracy. Your work will directly support **external audits** and investor reporting. This role offers hands-on experience with **ERP operations** across international markets.

You'll own the company's **video output end-to-end**, from shooting and editing to sound and delivery. Shape how the brand approaches **media-led storytelling** as a GTM and brand strategy. This hands-on role has real influence over scaling the function using **AI tools** across global offices.