Senior Software Engineer, Runtime

FuriosaAI
Seoul
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 5+ yearsEducation: bachelorsSkills: ["Communication","Requirements gathering","Technical alignment"]

Design and implement FuriosaAI’s low-level runtime stack that drives NPU hardware to its limits. Own DMA-based I/O and kernel execution scheduling, build asynchronous execution pipelines, and enable multi-node inference with RDMA communication primitives. Develop embedded firmware on the NPU’s integrated ARM core and profile/tune performance across firmware to user space to remove bottlenecks in real inference workloads.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
FuriosaAI
FuriosaAI
2 weeks ago

Senior Software Engineer, Runtime

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 1 hour agoStatus: Live

Job Summary

Design and implement FuriosaAI’s low-level runtime stack that drives NPU hardware to its limits. Own DMA-based I/O and kernel execution scheduling, build asynchronous execution pipelines, and enable multi-node inference with RDMA communication primitives. Develop embedded firmware on the NPU’s integrated ARM core and profile/tune performance across firmware to user space to remove bottlenecks in real inference workloads.
Location: Seoul
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Develop the low-level runtime for DMA-based I/O and kernel execution scheduling to maximize throughput and minimize latency.
  • •Build and optimize asynchronous execution pipelines for data movement and compute across NPU hardware.
  • •Enable multi-node inference by implementing communication primitives including RDMA-based inter-node data transfer.
  • •Develop embedded firmware (PERT) running on the NPU’s ARM core for on-device scheduling, synchronization, and hardware resource control.
  • •Profile and tune system-level performance across the full runtime stack to eliminate bottlenecks.

Key Requirements

  • •5+ years of systems programming experience using Rust, C, or C++.
  • •Solid understanding of computer architecture fundamentals including memory hierarchy, cache coherency, OS concepts, DMA, interrupts, and MMIO.
  • •BS degree in Computer Science, Engineering, or related field (or equivalent practical experience).
  • •Ability to gather requirements and drive technical alignment across teams with strong communication skills.
Experience:5+ years
Education:Bachelor's in Computer Science, Engineering, or a related field
Skills:CommunicationRequirements gatheringTechnical alignment
Languages:English
Tech Stack:RustCC++DMARDMARDMA-based data transferARMCUDACUDA GraphsLinux kernel modulesEBPFPerfFtraceE.g.

Company Brief

FuriosaAI
Designs and develops data‑center AI inference accelerators (RNGD) and a full stack hardware‑software platform to deliver energy‑efficient, high‑performance AI compute for enterprise and cloud customers.
Industry: Hardware Devices
Company Size: Medium (51 to 250 employees)
Growth: Scaleup
Valuation: USD 500M to 1B
Funding: Series C
Headquarters: Seoul, South Korea
Founded: 2017
Glassdoor
Glassdoor: 4.6
WebsiteLinkedInGlassdoor