Member of Technical Staff - Post Training Applied
Liquid AIVisit Liquid AI website
Liquid AI is an efficiency-first foundation-model company building device-native Liquid Foundation Models (LFMs) and tools to customize and deploy them.
Cambridge, Massachusetts, United States
Funding history
About Liquid AI
An MIT CSAIL spinout, Liquid AI develops general-purpose AI models focused on efficient deployment across CPUs, GPUs, NPUs, edge devices, and cloud or on-premises environments.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead text-model post-training engagements from scoping through delivery and evaluation. You will turn customer requirements into workflows, generate and assess text data, run fine-tuning and alignment methods, evaluate model performance, and build reusable applied tooling.
Requirements
- Experience with data generation and evaluation for LLM post-training
- Experience training or fine-tuning models using SFT, instruction tuning, RLHF, DPO, or similar methods
- Knowledge of text data quality and evaluation design
- Experience with chat-model alignment, instruction tuning, or text-data curation at scale
- Proficiency with Hugging Face, PyTorch, and modern model architectures
Responsibilities
- Own enterprise customer post-training engagements for text workloads
- Translate customer requirements into post-training specifications and workflows
- Design data-generation, filtering, and quality-assessment processes for text corpora
- Run supervised fine-tuning, instruction tuning, RLHF, DPO, and preference-alignment workflows
- Design and interpret task-specific text-model evaluations
- Build reusable applied tooling and workflows
Benefits
- Equity
- Medical, dental, and vision premiums fully paid for employees and dependents
- 401(k) matching up to 4% of base pay
- Unlimited PTO
- Company-wide Refill Days