Openings

NLP Engineer ๐ŸŒ

Responsibilities

  • ๋น„์›์–ด๋ฏผ ์•„๋™ ์Œ์„ฑ์˜ ํŠน์„ฑ(๋ฐœ์Œ ์˜ค์ฐจ, ๋ถ€์ •ํ™•์„ฑ ๋“ฑ)์„ ๊ทน๋ณตํ•˜๊ธฐ ์œ„ํ•œ ํŒŒ์ธ ํŠœ๋‹ ๋ฐ์ดํ„ฐ์…‹ ์…‹์—… ๋ฐ ๋ชจ๋ธ ๋ฏธ์„ธ ์กฐ์ •
    Build fine-tuning datasets and optimize speech recognition models to improve performance on non-native children's speech, addressing pronunciation errors and speech variability.
     

  • GOP ์•Œ๊ณ ๋ฆฌ์ฆ˜ ๊ธฐ๋ฐ˜์˜ ๋ฐœ์Œ ํ‰๊ฐ€ ๋ฐ ์Œ์†Œ ๋ ˆ๋ฒจ ์ ์ˆ˜ ์‹œ์Šคํ…œ ์„ค๊ณ„ ๋ฐ ๊ณ ๋„ํ™”
    Design, develop, and enhance pronunciation assessment systems and phoneme-level scoring based on the Goodness of Pronunciation (GOP) algorithm.
     

  • ๊ตญ์ฑ… ์—ฐ๊ตฌ๊ธฐ๊ด€(ETRI ๋“ฑ)์˜ ์Œ์†Œ ๋‹จ์œ„ ๋ฐœ์Œ ๋ถ„์„ ๋ฐ ์ž์œ ๋ฐœํ™”ํ˜• ์Œ์„ฑ์ธ์‹ ์—”์ง„ ์†Œ์Šค์ฝ”๋“œ ๋ถ„์„ ๋ฐ ๋‚ด์žฌํ™”
    Analyze, adapt, and integrate phoneme-level pronunciation analysis and spontaneous speech recognition engine source code developed by national research institutes (e.g., ETRI).

 

Qualifications

  • ์Œ์„ฑ ์ธ์‹(STT) ๋ฐ ์ž์—ฐ์–ด ์ฒ˜๋ฆฌ ํŒŒ์ดํ”„๋ผ์ธ ๊ตฌ์ถ• ๊ฒฝํ—˜์ด ์žˆ์œผ์‹  ๋ถ„
    Experience building speech recognition (STT) and natural language processing (NLP) pipelines.
     

  • ์Œํ–ฅ ๋ชจ๋ธ ๋ฐ ์Œ์†Œ ๋‹จ์œ„ ๋ถ„์„ ๊ธฐ์ˆ ์— ๋Œ€ํ•œ ๊นŠ์€ ์ดํ•ด๊ฐ€ ์žˆ์œผ์‹  ๋ถ„
    Strong understanding of acoustic models and phoneme-level speech analysis techniques.
     

  • ๊ธฐ์กด์— ํ•™์Šต๋œ ์Œ์„ฑ/NLP ์—”์ง„์„ ํŠน์ • ๋„๋ฉ”์ธ(์•„๋™ ๋ฐœ์Œ ๋“ฑ)์— ๋งž์ถฐ ํŒŒ์ธ ํŠœ๋‹ํ•ด ๋ณธ ๊ฒฝํ—˜์ด ์žˆ์œผ์‹  ๋ถ„
    Experience fine-tuning pre-trained speech recognition or NLP models for domain-specific applications, such as children's pronunciation.
     

  • ETRI, ์˜คํ”ˆ์†Œ์Šค ๋“ฑ ์™ธ๋ถ€ ๊ธฐ๊ด€์˜ AI API ๋˜๋Š” ์†Œ์Šค์ฝ”๋“œ๋ฅผ ์ด์ „๋ฐ›์•„ ์„œ๋น„์Šค์— ํฌํŒ…ํ•ด ๋ณธ ๊ฒฝํ—˜์ด ์žˆ์œผ์‹  ๋ถ„
    Experience integrating AI APIs or source code from external organizations (e.g., ETRI or open-source projects) into production services.
     

  • ์Œ์„ฑ ์ธ์‹ ๋ชจ๋ธ์˜ ๋ชจ๋ฐ”์ผ ํ”Œ๋žซํผ ์ด์‹ ๊ฒฝํ—˜์ด ์žˆ์œผ์‹  ๋ถ„
    Experience deploying and optimizing speech recognition models on mobile platforms.

 

Tech Stack

Python, PyTorch / TensorFlow, Hugging Face, Librosa, Audio Processing Tools

๋Œ“๊ธ€์€ ํšŒ์›๋งŒ ์ž‘์„ฑํ•  ์ˆ˜ ์žˆ์–ด์š”