Audio ML Engineer

Tasks:

As an Audio ML Engineer, you will:

• Own the delivery of ML models, acting as a bridge between Applied Science and Engineering teams.

• Architect and implement streaming audio services including ASR, TTS, VAD, and Diarization.

• Validate hardware/software compatibility across development and production environments (e.g., GPU types, OS, dependencies, audio I/O, codecs).

• Enforce rigorous testing protocols to ensure service-level awareness (stress/soak testing, quality preservation, latency consistency).

• Manage releases of new model versions, including rollback capabilities and integration consistency across components.

• Implement performance optimizations such as load management, dynamic batching, and caching.

• Develop observability systems including structured logging, tracing, health checks, alerting, and actionable metric dashboards.

Requirements

Must Have:

• 5+ years of experience in ML engineering, with a focus on audio and voice technologies.

• Strong background in Generative AI (LLMs, TTS) and Voice-based Conversational AI.

• Proven experience in:

  • Service & API engineering

  • Streaming implementation

  • Hardware/software compatibility validation

  • Stress testing and latency optimization

  • Model release management and rollback strategies

  • Integration impact assessment on end-to-end behavior

Nice to Have:

• Experience with performance optimization techniques (load management, batching, caching).

• Familiarity with observability tools and practices (logging, tracing, alerting, dashboards).

Offer

• Medicover healthcare package

• Multisport card

• Access to an e-learning platform

• Group life insurance