We are seeking an ASR Engineer to join our Solution Delivery team. You will be part of a talented software team that delivers the latest in Conversational AI and Virtual Agent technologies, bringing advanced voice-driven solutions to enterprises across the world.
As part of that team, you will be trained on Omilia’s Conversational AI platform and Speech to Text suite, working with cutting-edge technologies in signal processing and speech recognition.
Key Accountabilities:
- Audio signal processing. Corpus processing & management. Text normalization.
- Language modeling: Training, evaluating and optimizing language models for voice-enabled Conversational AI applications.
- Data augmentation for Language Models using various approaches including Generative AI.
- Phonetic lexicon curation.
- Developing and optimizing acoustic models for various languages, environmental conditions, and channels.
- Analyzing performance and optimizing existing Voice Activity Detection (VAD) models.
- Working with individuals from diverse backgrounds to analyze requirements and customize the ASR solution for enhancing the application's performance.
Requirements
- Academic Degree in Computer Science, Electrical Engineering, Computational Linguistics, Speech & Language Processing, related field, or equivalent experience.
- Junior Level Programming Knowledge, with a preference for BASH scripting; however, Python, Java, or C++ are also acceptable.
- Familiarity with any of the following: Digital Signal Processing, Language and Acoustic modeling concepts for ASR, Machine Learning algorithms, Phonetics and Phonology.
- Comfort working in a Linux environment.
- Excellent command of spoken and written English.
- Very good communication skills.
- Ambition, enthusiasm, and eagerness to learn, aptitude for analytical and creative thinking, with sharp attention to detail.
- Well-organized for both team and/ or solo assignments.
- Accountable within demanding deadlines.
Nice to have:
- Experience working with ASR platforms such as Kaldi.
- Experience with speech analysis software such as Praat.
- Experience with voice-enabled conversational automated dialog systems. Experience in any other production-level ASR/NLU/NLP solutions will also be considered a plus.
- Familiarity with ML frameworks such as Pytorch.
- Knowledge of additional languages (preferably Spanish, French, and/or German).
- Familiarity with GitLab and Jira
Benefits
- Fixed compensation;
- Long-term employment with the working days vacation;
- Development in professional growth (courses, training, etc);
- Being part of successful cutting-edge technology products that are making a global impact in the service industry;
- Proficient and fun-to-work-with colleagues;
- Apple gear.