Description

Develop and maintain large-scale, carrier-grade automatic speech recognition systems and related products.

This role is on-site.

Responsibilities

• Develop software, algorithms, and API designs primarily using Java, Python, and C++.
• Extend and maintain large-scale, carrier-grade automatic speech recognition systems.
• Research and implement state-of-the-art features and acoustic modeling mechanisms.
• Optimize language models and decoder algorithms to improve performance.
• Document all technical designs and procedures in detail.

Required Skills

• 5+ years of software engineering experience.
• Proficiency in Java, C/C++, and Python for runtime analysis and design.
• Deep knowledge of statistical probability theory and speech algorithms.
• Expertise in HMM, GMM, FST, acoustic modeling, and advanced machine learning.
• Experience with Statistical Language Modeling (SLM), NLP, or Information Retrieval (IR).
• Ability to read, adapt, and implement algorithms from academic journals and papers.
• Knowledge of mainstream speech recognition software, DSP theory, feature extraction, scripting, and parsing.

Preferred Skills

• Experience designing and running ASR experiments using HTK or KALDI.

Key Skills

Education

Any Graduate