Software Engineer (Quantization Engineer)

furiosa-aiΒ· Algorithm
Apply Now β†—
🌍 RemoteπŸ“ Seoul HQFullTime

About this role

About Algorithm Team - Model Compression Part

LLM Quantization이 μΆ”λ‘  νš¨μœ¨μ„±μ„ κ·ΉλŒ€ν™”ν•  수 μžˆλ‹€λŠ” 점은 널리 μ•Œλ €μ Έ μžˆμŠ΅λ‹ˆλ‹€. κ·ΈλŸ¬λ‚˜ 이λ₯Ό μ‹€μ œ μ„œλΉ„μŠ€μ— μ μš©ν•˜λŠ” 것은 μ—¬μ „νžˆ μ–΄λ €μš΄ κ³Όμ œμž…λ‹ˆλ‹€. Model Compression PartλŠ” μ‚¬μš©μž μΉœν™”μ μΈ Model Compression 도ꡬλ₯Ό κ°œλ°œν•΄ μ΄λŸ¬ν•œ 어렀움을 ν•΄κ²°ν•˜κ³ , 고객이 μžμ‚¬ NPUλ₯Ό 졜고의 효율둜 ν™œμš©ν•  수 μžˆλ„λ‘ μ§€μ›ν•˜λŠ” 것을 λͺ©ν‘œλ‘œ ν•©λ‹ˆλ‹€.

Model Compression 도ꡬ가 Hardware-specific μ΅œμ ν™”λ₯Ό 포함할 λ•Œ, νš¨μœ¨μ„±μ„ κ·ΉλŒ€ν™”ν•  수 μžˆμŠ΅λ‹ˆλ‹€. μš°λ¦¬λŠ” μ΄λŸ¬ν•œ μš”κ΅¬λ₯Ό μΆ©μ‘±ν•˜κΈ° μœ„ν•΄ μžμ‚¬ NPU에 νŠΉν™”λœ μ΅œμ ν™” κΈ°λŠ₯을 κ°–μΆ˜ 자체 도ꡬλ₯Ό κ°œλ°œν•˜μ˜€μœΌλ©°, 이λ₯Ό 톡해 NPU의 μ„±λŠ₯을 μ΅œλŒ€λ‘œ λŒμ–΄μ˜¬λ¦΄ 수 μžˆλŠ” ν•„μˆ˜ μ†Œν”„νŠΈμ›¨μ–΄ μŠ€νƒμ„ μ œκ³΅ν•©λ‹ˆλ‹€.

FuriosaAI Model Compression λ„κ΅¬λŠ” μžλ™ν™”, ν™•μž₯μ„±, μ•ˆμ •μ„±μ„ μ§€μ†μ μœΌλ‘œ κ°œμ„ ν•˜λ©΄μ„œ 점점 더 λ§Žμ€ κΈ°λŠ₯이 μš”κ΅¬λ©λ‹ˆλ‹€. 이에 따라 μ†Œν”„νŠΈμ›¨μ–΄ μ—”μ§€λ‹ˆμ–΄λ§ μ—­λŸ‰μ΄ 맀우 μ€‘μš”ν•œ μƒν™©μž…λ‹ˆλ‹€. λ”°λΌμ„œ ν’λΆ€ν•œ μ†Œν”„νŠΈμ›¨μ–΄ μ—”μ§€λ‹ˆμ–΄λ§ κ²½ν—˜μ„ λ³΄μœ ν•˜κ³  있으며, Model Compression μ—”μ§€λ‹ˆμ–΄λ‘œμ„œ 컀리어λ₯Ό λ°œμ „μ‹œν‚€κ³ μž ν•˜λŠ” 인재λ₯Ό μ°Ύκ³  μžˆμŠ΅λ‹ˆλ‹€.

Responsibilities

  • Model Compression 도ꡬ 개발

  • λ‹€μ–‘ν•œ μ–‘μžν™”λœ λͺ¨λΈ 확보 및 μ„±λŠ₯ 검증

  • 이λ₯Ό 기반으둜 더 μ§„λ³΄λœ Compression Algorithm개발

Minimum Qualifications

  • PyTorch 개발 κ²½ν—˜μ΄ ν’λΆ€ν•˜μ‹  λΆ„

  • μƒμš© μ†Œν”„νŠΈμ›¨μ–΄ 개발 κ²½ν—˜μ΄ μžˆμœΌμ‹  λΆ„

  • κ΄€λ ¨ λΆ„μ•Όμ—μ„œ 3λ…„ μ΄μƒμ˜ 싀무 κ²½λ ₯을 λ³΄μœ ν•˜μ‹  λΆ„

Preferred Qualifications

  • DevOps 및 MLOps에 λŒ€ν•œ κ²½ν—˜κ³Ό 지식

  • vLLM, TensorRT-LLM λ“±μ˜ LLM inference tool을 μ‚¬μš©ν•œ κ²½ν—˜

  • Deep Learning Quantization κ²½ν—˜κ³Ό 지식

  • Deep Learning 가속과 κ΄€λ ¨λœ νšŒμ‚¬μ—μ„œμ˜ 근무 κ²½ν—˜

Contact

Frequently Asked Questions

Is the salary disclosed for the Software Engineer (Quantization Engineer) position at furiosa-ai?
The salary for this Software Engineer (Quantization Engineer) role at furiosa-ai is not publicly listed. Click "Apply Now" to learn more about the compensation package on their official careers page.
Is the Software Engineer (Quantization Engineer) job at furiosa-ai remote?
Yes, this Software Engineer (Quantization Engineer) position at furiosa-ai is remote, with team members based in Seoul HQ. You can work from home or anywhere in the supported regions.
Is the Software Engineer (Quantization Engineer) role at furiosa-ai full-time or part-time?
This is listed as a FullTime position. It is posted as a Software Engineer (Quantization Engineer) role in the Algorithm department at furiosa-ai.
Which team or department does the Software Engineer (Quantization Engineer) at furiosa-ai belong to?
This Software Engineer (Quantization Engineer) position is part of the Algorithm department at furiosa-ai. See the full job description for more information about the team structure and responsibilities.
How do I apply for the Software Engineer (Quantization Engineer) position at furiosa-ai?
Click the "Apply Now" button on this page. You will be redirected to furiosa-ai's official application portal hosted on ashby where you can submit your application directly.
When was the Software Engineer (Quantization Engineer) job at furiosa-ai posted?
This Software Engineer (Quantization Engineer) position at furiosa-ai was posted on Oct 3, 2025. Apply as soon as possible β€” early applications are often reviewed first.
Software Engineer (Quantization Engineer)
furiosa-ai
Apply for this role β†—

You'll be redirected to furiosa-ai's official application page on Ashby ATS.