Software Engineer, AI Model Enablement & Inference

FuriosaAI · Software · Seoul
공고 번호 4006985201

새 LLM을 분석하고 NPU용 모델 kernel과 추론 실행 경로를 구현·검증.

학위 제한 미명시 · 도전 지원

확인할 점: 텐서 연산/가속기 kernel 구현·최적화, Rust/C++ 추론 코드 경험은 미확인.

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 adapt task-specific models and verify the input and output requirements needed for successful inference.

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 developed business-card extraction that reached 94% accuracy across seven core fields. I applied teacher-student knowledge distillation and LoRA fine-tuning; separate difficult-case evaluation improved from 30.2% to 65.3% through further training and output correction.

I bring experience adapting models and making their trained behavior reproducible in serving. My work combines teacher-student training, parameter-efficient fine-tuning, and practical checks of the inputs and output handling that determine task success. At FuriosaAI, I can contribute model integration and reference-based validation, tracing discrepancies from model inputs through inference outputs. My experience taking trained models into APIs provides a practical basis for improving model support.

Cover Letter

PDF 첨부 또는 Enter manually에 붙여 넣기.

Dear FuriosaAI Hiring Team,

I am applying for the Software Engineer, AI Model Enablement & Inference position (Job ID 4006985201). I bring experience adapting models and making their trained behavior reproducible in serving. My work combines teacher-student training, parameter-efficient fine-tuning, and practical checks of the inputs and output handling that determine task success. 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 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.

I developed business-card information extraction used in TieMing, reaching 94% accuracy across seven core fields in a workflow covering approximately 5,000 cards. To address correct text being assigned to the wrong fields, I trained a smaller student model through knowledge distillation and low-rank adaptation (LoRA). I separately targeted difficult cases: follow-up training and selective regeneration of malformed outputs raised field-value accuracy from 30.2% to 65.3%. The work involved choosing the training method, diagnosing output errors, and implementing the changes in the extraction workflow.

At FuriosaAI, I can contribute model integration and reference-based validation, tracing discrepancies from model inputs through inference outputs. My experience taking trained models into APIs provides a practical basis for improving model support.

Sincerely,
Jeonghun Kim