about-project :

responsibilities :

Deliver ML models as an interface between Applied Science and Engineering
Architect and implement streaming audio services
Validate hardware/software compatibility in dev and prod environments
Perform stress, soak, and quality tests to ensure consistent latency and service quality
Manage model version releases with rollback capability
Optimize performance (load management, dynamic batching, caching)
Implement observability systems (logging, tracing, health checks, alerting, dashboards).

requirements-expected :

Experience with Generative AI (LLMs, TTS) and Voice-based Conversational AI
Strong skills in service/API engineering, streaming implementation, and hardware/software compatibility validation
Proven experience in stress testing, quality preservation, and latency management
Experience in integration and release management for production models

offered :

Private medical care with dental care (covering 70% of costs) + rehabilitation package. Family package option possible.
Multisport card (also for an accompanying person).
Life insurance.
International work environment