Production Engineer, LLM Serving

FuriosaAI · Software · Seoul
공고 번호 4006969201

LLM 서빙 서비스의 지연·처리량·자원 사용과 장애 복구를 운영·개선.

학사 명시 · 도전 지원

확인할 점: 필수 3년 production 경력과 Kubernetes 운영 근거 부족. 현업은 인턴 포함 약 13개월.

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 build inference services and GPU processing jobs with explicit resource controls and recovery behavior.

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 build and operate vLLM and FastAPI model services with Docker deployment and service/GPU monitoring. I ran distributed training on two RTX 4090 GPUs with checkpoint recovery and now also use two A100 GPUs through NIPA's support program.

I bring hands-on experience deploying model APIs and redesigning GPU processing when request handling became a bottleneck. I take responsibility for whether a model result reaches the caller, including resource use, job progress, and restart recovery. At FuriosaAI, I can contribute serving workload analysis, deployment, and recovery design. I would combine request traces with GPU measurements to locate bottlenecks and validate changes against both completion behavior and elapsed time.

Cover Letter

PDF 첨부 또는 Enter manually에 붙여 넣기.

Dear FuriosaAI Hiring Team,

I am applying for the Production Engineer, LLM Serving position (Job ID 4006969201). I bring hands-on experience deploying model APIs and redesigning GPU processing when request handling became a bottleneck. I take responsibility for whether a model result reaches the caller, including resource use, job progress, and restart recovery. 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 take responsibility for model deployment as well as training, building vLLM and FastAPI inference services in Docker with Prometheus and Grafana monitoring. Watching service failures alongside GPU usage helps me distinguish application problems from resource constraints. I ran distributed training on two RTX 4090 GPUs with BF16 precision and checkpoint recovery, and now also use two A100 GPUs through a national computing-support program. I track experiments in Weights & Biases so model changes can be compared across runs.

At FuriosaAI, I can contribute serving workload analysis, deployment, and recovery design. I would combine request traces with GPU measurements to locate bottlenecks and validate changes against both completion behavior and elapsed time.

Sincerely,
Jeonghun Kim