Senior Machine Learning Engineer, ASR Confidence Engine

In this role you’ll build models estimating confidence of automatic speech recognition (ASR). Among other things, confidence estimation is an important part of large scale automated labeling, ASR models arbitration, and robust low resource command recognition. Besides confidence models, you will also improve various aspects of our ASR technology.

In this role, you will:

• Work independently and lead technical initiatives to advance confidence models architecture
• Collaborate with cross-functional teams to support confidence models for a variety of ASR architectures, sizes, and languages
• Find novel ways to utilize confidence estimates
• Train, tune and test state-of-the-art ASR models for SoundHound voice AI products using machine learning and deep learning techniques

We would love to hear from you if:

• You have a Bachelor's degree in Computer Science, Electrical Engineering, Math, Physics or other relevant disciplines with 8 years of full-time work experience, a Master’s degree with 6 years of work experience, or a PhD with 3 years of work experience
• You have experience in automatic speech recognition, natural language understanding, or other spoken language processing field. Especially, if you’ve worked with both end-to-end and hybrid ASR models
• You have good understanding of machine learning fundamentals, and are proficient in machine learning frameworks (pytorch in particular, but experience with xgboost and other frameworks is also welcome)
• You are proficient in writing Python code that is documented, well tested, packaged, and follows industry best practices. Experience with C++ is also appreciated
• You have experience with Kubernetes, Docker, and other containerization technologies in cloud service environment
• You have experience leading technical initiatives

We’d be especially excited if your MSc/PhD thesis is about ASR, you have publications in relevant conferences (Interspeech/ICASSP/NeurIPS etc), or you have experience with on-device ASR (e.g. using TorchScript).

This role is available throughout Germany. Employees within a 100-kilometer radius of our Berlin office are expected to work from the office on three pre-scheduled “core days” each month to encourage cross-team connection and in-person collaboration. Aside from these office-specific “core days,” this job allows for virtual/remote, hybrid, and in-office workplace options. In addition to salary and equity, you will receive comprehensive healthcare, paid time off, and other benefits. Our recruiting team will provide a specific salary range based on location and years of experience.

_____________________

#LI-REMOTE

#LI-MR1