Senior Software Engineer, Runtime

FuriosaAI
Seoul
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 3+ yearsEducation: bachelorsSkills: ["Communication","Technical alignment","Requirements gathering"]

Design and implement the low-level runtime stack that drives FuriosaAI’s NPU hardware to maximize inference throughput and minimize end-to-end latency. Build DMA-based I/O and kernel execution scheduling, develop asynchronous execution pipelines for orchestrating data movement and compute, and enable multi-node inference using RDMA-based communication primitives. Develop embedded firmware (PERT) and profile/tune performance across firmware and user-space to remove bottlenecks in real workloads.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
FuriosaAI
FuriosaAI
1 week 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: 12 minutes agoStatus: Live

Job Summary

Design and implement the low-level runtime stack that drives FuriosaAI’s NPU hardware to maximize inference throughput and minimize end-to-end latency. Build DMA-based I/O and kernel execution scheduling, develop asynchronous execution pipelines for orchestrating data movement and compute, and enable multi-node inference using RDMA-based communication primitives. Develop embedded firmware (PERT) and profile/tune performance across firmware and user-space to remove bottlenecks in real 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 reduce latency.
  • •Build and optimize asynchronous execution pipelines to orchestrate data movement and compute across NPU hardware.
  • •Implement foundational multi-node communication primitives, including RDMA-based data transfer.
  • •Develop embedded firmware (PERT) running on the NPU’s integrated ARM core for scheduling, synchronization, and hardware resource control.
  • •Profile and tune system-level performance across firmware to user-space to eliminate bottlenecks in real inference workloads.

Key Requirements

  • •BS degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
  • •3+ years of systems programming experience using Rust, C, or C++.
  • •Strong understanding of computer architecture fundamentals (memory hierarchy, cache coherency, OS, DMA, interrupts, MMIO).
  • •Ability to communicate effectively and gather requirements to drive technical alignment across teams.
Experience:3+ yearsAI computeNPUSystems programmingLow-latency runtimeEmbedded firmwareDistributed/multi-node inference
Education:Bachelor's in Computer Science
Skills:CommunicationTechnical alignmentRequirements gathering
Tech Stack:RustCC++ARMDMAMMIORDMACUDACUDA GraphsLinux kernel modulesEBPFPerfFtraceScatter-gather I/OZero-copy

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