Senior Solution Architect
FuriosaAI is a South Korean AI semiconductor company building energy-efficient inference accelerators, servers, and software for enterprise and cloud AI deployments.
Funding history
Investors
About FuriosaAI
FuriosaAI develops the RNGD AI inference accelerator and NXT RNGD Server, alongside a software toolchain for compiling, optimizing, and deploying LLM and agentic-AI workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will define customer requirements and constraints, design solution architectures, and set proof-of-concept goals, scope, and success criteria. You will compare technical alternatives based on performance, accuracy, and implementation complexity, while explaining your decisions. You will lead proof-of-concepts and performance-improvement work through direct implementation and validation. You will communicate results so customers can use them for decisions, coordinate priorities across customer and internal stakeholders, and guide resolution of key technical issues.
Requirements
- Bachelor's degree in computer science or a related field, or equivalent experience
- Write and modify Python programs and analyze execution results and errors
- Analyze problem causes using data and experiments and validate solutions
- Clearly explain technical content and decision rationale and collaborate by asking for and sharing needed information
- Demonstrate capabilities through professional, academic, research, internship, personal-project, or open-source experience
- Experience developing and operating in Linux environments
- Experience with C, C++, or Rust
- Experience automating development, testing, or benchmarking with scripts
- Experience with LLM serving and inference optimization tools such as vLLM, SGLang, or TensorRT-LLM
- Experience with Docker or Kubernetes
- Experience designing benchmarks or evaluating model accuracy
- Experience in presales or B2B technical support
Responsibilities
- Analyze customer requirements and technical constraints and propose inference solutions
- Develop and improve inference programs, examples, and demos using the Furiosa SDK
- Validate technical feasibility through proof-of-concepts and document results and technical issues
- Evaluate inference performance, latency, throughput, and model accuracy
- Analyze changes from SDK updates and differences from GPU and other execution environments
- Explain product capabilities and validation results to customers, partners, and developers
- Create usage guides and training materials
- Share customer technical issues and feedback with engineering stakeholders
- Define solution architectures and proof-of-concept goals, scope, and success criteria
- Compare technical alternatives and explain selection rationale
- Lead proof-of-concepts and performance-improvement initiatives
- Coordinate priorities and guide resolution of key technical issues