F

FuriosaAI

Power-efficient AI inference accelerator chips

Solution Architect

Pre-Sales Solution EngineeringConfirmed live in the last 24 hours
Full-timeSeoul, South KoreaNo salary listedIn-person

About the Job

Requirements

  • A bachelor's degree or higher in Computer Science or a related field, or equivalent experience.
  • Ability to write and modify programs in Python and analyze execution results and errors.
  • Ability to analyze problem causes using data and experiments and validate solutions.
  • Ability to explain technical content and reasoning clearly, ask for needed information, share information, and collaborate.
  • Experience may be demonstrated through professional work, study, research, internships, personal projects, or open-source activities.

Responsibilities

  • Analyze customer problems and technical constraints, and propose suitable inference environments and implementation approaches.
  • Develop and improve inference programs, examples, and demos using the Furiosa SDK.
  • Verify technical feasibility through proofs of concept based on customer requirements, and document results, key technical issues, and implementation considerations.
  • Define measurement conditions and evaluate inference performance, including latency and throughput, and model accuracy.
  • Analyze changes associated with SDK updates and differences from other execution environments such as GPUs.
  • Explain product characteristics and validation results to customers, partners, and developers, and prepare usage guides and training materials.
  • Share technical issues and feedback identified in customer environments with internal engineering teams, and discuss solutions and product improvement directions.
  • Clarify customer requirements and constraints and design solution architectures, proof-of-concept goals, scope, and success criteria.
  • Compare alternatives based on performance, accuracy, and implementation complexity, and provide the rationale for technical choices.
  • Participate directly in implementation and validation, lead proof-of-concept and performance-improvement tasks, and explain results so customers can use them in decision-making.
  • Coordinate priorities between customers and internal teams and recommend approaches for resolving major technical issues.

Desired Qualifications

  • Experience developing and operating in Linux environments.
  • Development experience using C, C++, or Rust.
  • Experience automating development, testing, or benchmarking tasks with scripts.
  • Experience using LLM serving and inference-optimization tools such as vLLM, SGLang, or TensorRT-LLM.
  • Experience using Docker or Kubernetes.
  • Experience designing benchmarks or evaluating model accuracy.
  • Presales or B2B technical support experience.

About the Company

FuriosaAI

Power-efficient AI inference accelerator chips

FuriosaAI develops AI accelerators for data centers. Its flagship RNGD chip is a power-efficient accelerator designed to boost performance per watt for running large language models and other demanding AI workloads. The hardware is configurable with multiple processing elements to fit different workloads, and it is paired with advanced compiler technology and profiling tools to identify bottlenecks and optimize efficiency. This combination of flexible hardware and software optimization differentiates FuriosaAI from competitors, focusing on maximizing performance while keeping energy use low. The company targets data centers and enterprises that need high-performance, energy-efficient AI solutions, and aims to make AI computing more sustainable and scalable by selling its chips and related software tools and pursuing long-term contracts with large-scale customers.

Company size
201-500
Company stage
Series D
Total funding
$887.5M
Headquarters
Seoul, South Korea
Founded
2017

Recently Posted Jobs

Explore more opportunities at FuriosaAI

See more jobs