Member of Technical Staff, LLM Post-Training, Applied
Sanas · Palo Alto, CA
Applied AIonsitesenior
At a glance
Highlights
- Own applied LLM post-training end-to-end for self-hosted products.
- Adapt open-source LLMs for reliable high-stakes on-premise deployment.
- Take models from customer needs to shipped production workloads.
Ideal candidate
An outcome-driven ML engineer with 5+ years shipping production systems who owns customer projects end-to-end and cares deeply about data quality, evaluation, and making language models work reliably in the real world.
Requirements
- 5+ years building and deploying ML-based services in production
- Hands-on data generation and evaluation for LLM post-training
- Training or fine-tuning with SFT, instruction tuning, RLHF, DPO or similar
- Strong intuition for text data quality and evaluation design
- Experience with chat alignment, instruction tuning, text curation at scale
- Experience with Agentic AI
- Proficiency with Hugging Face, PyTorch and modern model architectures
- remote policy
- On-site in Palo Alto minimum 4 days per week
Lab profile
About Sanas
Real-time speech AI platform for accent translation, noise cancellation, and clearer communication.
What they build
- Real-time speech AI platform
- Accent translation
- Noise cancellation
Known for
- Real-time speech processing
- ML inference engineering
- LLM post-training
- Developer platform and SDKs
First seen · Last seen