TA
$200,000 – $260,000
Listed on Together AI’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
Senior ML engineer responsible for optimizing how Together AI serves voice models like Whisper and Parakeet on GPU hardware, with focus on inference latency, throughput, and production-grade reliability. Suits engineers with deep model-serving and infrastructure experience who want to shape a foundational product in real-time voice AI.
Our summary, not Together AI’s wording. The full posting is on their site.
What they ask for
Required
- 5+ years ML engineering experience with focus on model serving or inference optimization
- Hands-on experience modifying LLM serving engine internals (vLLM, SGLang, TensorRT-LLM or similar)
- Strong Python and PyTorch proficiency
- GPU profiling and optimization skills including CUDA and memory management
- Track record shipping ML systems to production with measurable improvements
- Product sense for developer needs in voice applications
- Ability to work on small early-stage team with multiple responsibilities
Nice to have
- Experience with speech and audio ML including ASR and TTS architectures
- Audio signal processing knowledge
- Familiarity with audio codecs and tokenization schemes
- Experience training or fine-tuning speech models