Liquid AI
Member of Technical Staff - Post Training, Applied (Audio)
San Francisco +2 · Hybrid · Staff · Full-time · Posted Mar 30, 2026
- Location
- San Francisco
Remote
Boston
About the job
Owns enterprise post-training projects that adapt Liquid’s audio models for customer use cases, including spoken-intent function calling, evaluation, and production delivery.
What you'll do
- Translate customer requirements into post-training specifications and workflows for audio models.
- Build function-calling capabilities and data-generation pipelines for audio models.
- Run model training and alignment workflows, evaluate performance, and feed findings into core pipelines.
What they ask for
- Hands-on experience with language-model post-training (SFT, preference alignment, and/or RL).
- Experience with data-generation and evaluation pipelines for LLM or audio-model training.
- Strong intuition for data quality and evaluation design.
- Familiarity with function calling, tool use, or structured-output training for language models.
Nice to have
- Experience with speech or audio language models, or customer-facing/applied ML delivery.
- Experience with alignment or RL beyond basic supervised fine-tuning, or familiarity with on-device or low-latency inference constraints.
Tools
LFM2.5-Audio, SFT, RL, ASR, TTS
AI focus
Adapt audio language models for enterprise deployment, especially spoken-intent recognition and tool calling, using data generation, supervised fine-tuning, preference alignment, reinforcement learning, and task-specific evaluation.
Model-written summary · the original posting is authoritative