Software - Software Engineer, Compiler (Kernel Optimization)

FuriosaAI · Software · Seoul, South Korea
공고 번호 4007040201

AI compiler와 kernel의 실행 병목을 분석하고 병렬 연산·메모리 이동 최적화.

학사 명시 · 도전 지원

확인할 점: low-level/performance-critical SW, 하드웨어 병목 profiling·병렬 메모리 최적화 근거 부족.

영문 이력서 PDF ↗영문 이력서 Overleaf ZIP ↓

Cover Letter PDF ↗Cover Letter Overleaf ZIP ↓

이 공고의 지원서 열기 ↗

Career Summary

필수 Career Summary 칸에 붙여 넣기.

I am an ML engineer and AI Researcher at ISPARK R&D Center responsible for TieMing's core AI features, from model training to inference APIs and deployment. I bring a multimodal research background—five publications, four as first author—and turn experimental results into working products. I improve workload execution through measured implementation changes, checking outputs alongside elapsed time.

I reduced server processing time by 36.9% on a 30-minute recording through speech-region batching. I also redesigned long-audio processing as recoverable asynchronous jobs, separating completion and recovery from the HTTP request lifetime.

I improved normalized database-result agreement from 26.6% to 76.6% on a 64-question internal CRM development benchmark through teacher-student training and LoRA. I also verified and documented the schema input required to reproduce the model's behavior in serving.

I bring experience translating a measured bottleneck into an implementation change and validating the result on fixed inputs. My work includes speech-processing optimization and task-specific model evaluation, with performance and output quality checked separately. At FuriosaAI, I can contribute representative workloads, reference checks, and focused performance investigations. I would reproduce a bottleneck, examine the operation's constraints, and validate numerical behavior across input variations as I develop an optimization.

Cover Letter

PDF 첨부 또는 Enter manually에 붙여 넣기.

Dear FuriosaAI Hiring Team,

I am applying for the Software - Software Engineer, Compiler (Kernel Optimization) position (Job ID 4007040201). I bring experience translating a measured bottleneck into an implementation change and validating the result on fixed inputs. My work includes speech-processing optimization and task-specific model evaluation, with performance and output quality checked separately. Before ISPARK, I served one year as an information-systems NCO in the Republic of Korea Air Force (Dec 2021–Dec 2022), maintaining Linux servers through shell scripting and log analysis.

I redesigned long-audio processing and reduced server processing time by 36.9%, from 122.6 to 77.4 seconds on a 30-minute recording, using Silero voice activity detection and faster-whisper batching at batch size 8. The same workload had also exposed a delivery problem: the server finished after the synchronous HTTP request timed out. I separated live sessions from recoverable asynchronous jobs, with task polling and persisted progress. I treated recognition quality, execution time, and delivery as separate engineering problems, allowing each change to address a specific cause.

I improved a four-billion-parameter Text-to-SQL model from 26.6% to 76.6% normalized database-result agreement on a 64-question internal CRM development benchmark, using teacher-student training and rank-16 LoRA. The model matched 49 of 64 reference results, compared with 17 for the base model; scoring ignores row order and normalizes numbers and dates. I also verified the serving interface: missing schema input caused invented table names despite unchanged weights. I documented the required schema inputs alongside the adapter so the trained behavior could be reproduced in serving.

At FuriosaAI, I can contribute representative workloads, reference checks, and focused performance investigations. I would reproduce a bottleneck, examine the operation's constraints, and validate numerical behavior across input variations as I develop an optimization.

Sincerely,
Jeonghun Kim