FuriosaAI

Software Engineer, Compiler (Middle-end)

Open 65d APACMiddle

FuriosaAI is seeking a Software Engineer to develop middle-end compiler optimizations for their AI inference hardware. The role involves designing IR abstractions, scheduling algorithms, and performance models to improve the efficiency of deep learning workloads on specialized compute platforms.

AI Deep Learning GPU

Software Engineer, Kernel Programming

Open 65d APACContract

FuriosaAI is seeking a Software Engineer to design and implement high-performance kernels for their proprietary AI-native compute platform. The role involves optimizing AI model performance on hardware, developing diagnostic tools, and enabling end-to-end programming for AI workloads.

AI Deep Learning GPU Tcl

Software Engineer, Kernel Programming Model

AI C++ PyTorch Rust Technical Evangelism

Design PyTorch-native kernel integration layers and runtime environments to execute custom AI kernels efficiently within PyTorch, optimizing for hardware control and tensor programmability.

Software - Software Engineer, Compiler (Kernel Optimization)

Open 35d APAC

AI Deep Learning GPU LLM Tcl +1 skills

Software engineer on FuriosaAI's compiler team in Seoul who owns the performance of critical AI kernels in Furiosa-LLM: analyzing LLM serving workloads, finding bottlenecks, and writing highly optimized kernels in TCL (Tensor Contraction Language), plus developing scheduling and specialization techniques for dynamic serving workloads.

Software Engineer, AI Model Enablement & Inference

Open 35d APAC

AI C++ CUDA LLM Machine Learning +7 skills

Software engineer on FuriosaAI's MLSys team enabling frontier LLMs on the company's NPU chips: analyzing model architectures, writing and optimizing Tensor Contraction Language (TCL) kernels (attention, MoE), integrating models into the Furiosa-LLM inference stack, and validating correctness and performance. Core stack: Python, PyTorch, TCL DSL, with Rust/C++ code reading and vLLM/SGLang technique

Software Engineer, Build Systems & Release Infrastructure

Open 35d APAC

AI Automation Bash Bazel CentOS +12 skills

About FuriosaAI FuriosaAI builds high-performance, high-efficiency AI compute for the Inference Era. Founded in 2017 by veteran semiconductor and AI algorithm engineers, Furiosa operates globally with offices in Korea…

Systems Software Engineer, Power, Performance, and Thermal (PPT)

Open 65d RemoteAPAC

AI Assembly C++ Embedded Linux Firmware +3 skills

Develops firmware/software for NPU management interfaces, handling communication between host systems and AI accelerators. Focuses on power, performance, and thermal telemetry, protocol compliance (MCTP/PLDM), and system-level validation for AI hardware.

Systems Software Engineer, PCIe Device Driver

AI API Firmware GDB HPC +4 skills

Develop and maintain Linux PCIe device drivers and kernel modules for FuriosaAI's AI-native compute platform, optimizing DMA, IOMMU, and high-performance I/O pipelines.

Systems Software Engineer, NPU Management Interface

AI C++ Embedded Systems Firmware GPU +3 skills

Develops firmware/software for NPU management interfaces, handling communication between host systems and AI accelerators via protocols like MCTP/PLDM, while ensuring telemetry, health monitoring, and compliance with industry specs.

Software Engineer, AI Application

FuriosaAI is seeking a Software Engineer to develop AI reference applications and maintain internal services to support their AI-native compute platform. The role involves building RAG and agentic systems, creating sample code, and collaborating with the global developer community.

Agentic AI AI GitHub

Software Engineer, Agent System Developer

Agentic AI AI Ai Enablement CLI C++ +4 skills

Builds and optimizes an agent system framework for AI-driven automation, integrating LLM-based reasoning, tool execution, and orchestration in a production environment.

Senior Software Engineer, Runtime

Open 65d APACSenior

AI C++ CUDA Deep Learning Firmware +5 skills

FuriosaAI is seeking a Senior Software Engineer to design and implement the low-level runtime stack for their NPU hardware. The role involves developing firmware, optimizing asynchronous execution pipelines, and enabling multi-node inference using Rust, C, or C++.

Senior Software Engineer, Inference Engine (Platform Software)

Open 65d APACSenior

AI C++ CUDA Deep Learning Generative AI +5 skills

Build and optimize a high-performance inference engine for LLMs and multimodal models on FuriosaAI’s NPUs, collaborating with compiler and hardware teams to maximize throughput and efficiency.

furiosa-ai

11 months ago

SoC Software Engineer

Open 128d APAC

AI C++ Embedded Systems Firmware FPGA +2 skills

Responsibilities Develop and maintain ROM code and early system initialization software Port and customize Arm Trusted Firmware (TF-A / TF-M) Implement system trust primitives such as Secure Boot , firmware update, and…