Senior Speech & NLP ML Engineer

Svitla Systems is seeking a Senior Speech & NLP ML Engineer to join a project for an American mobile computing company. You will play a key role in developing, optimizing, and improving end-to-end speech processing pipelines, ensuring high-quality transcription and model performance.

Key responsibilities

• Develop, train, evaluate, and deploy machine learning models for speech and audio-related tasks.
• Build and optimize end-to-end speech-to-text pipelines, including audio preprocessing, ASR, and transcript post-processing.
• Prepare, clean, and manage audio and text datasets for model development and evaluation.
• Analyze ASR outputs and identify ways to improve transcription quality through data improvements and model tuning.
• Apply NLP techniques for transcript cleanup, text normalization, and domain-specific correction.

Requirements

• Strong Python programming skills and solid knowledge of machine learning and AI.
• Hands-on experience with automatic speech recognition (ASR) or speech-to-text systems.
• Experience building or improving audio preprocessing and transcription pipelines.
• Familiarity with deep learning frameworks such as PyTorch and audio/ML tooling like Hugging Face, torchaudio, or librosa.
• Ability to independently own tasks, analyze performance, and proactively propose technical improvements.

What we offer

• Engagement in US and EU projects based on advanced technologies.
• Regular performance appraisals to support your professional growth.
• Personalized learning programs tailored to your interests and skill development.
• Generous time off, including vacation, national holidays, and sick leaves.
• Access to free tech webinars and a supportive, collaborative remote team environment.