Member of Technical Staff - Post Training, Applied

The role

You will own applied post-training for text workloads by adapting Liquid Foundation Models for enterprise customers. You will translate business needs into models and build reusable tooling and workflows.

What you will do

• Own enterprise post-training engagements for workloads.
• Translate customer requirements into technical specifications, delivery plans, and evaluation criteria.
• Build data generation, curation, filtering, and quality assessment workflows.
• Select and execute post-training methods including SFT, instruction tuning, RLHF, and DPO.
• Design task-specific evaluations and analyze model failures.
• Deliver adapted models with performance evidence and documented limitations.
• Build reusable tooling and workflows to accelerate future engagements.

Required qualifications

• Strong judgment in data quality and evaluation design.
• Hands-on experience generating, curating, and evaluating data for LLM post-training.
• Experience training or fine-tuning language models using SFT, instruction tuning, RLHF, DPO, or similar preference alignment approaches.
• Practical experience in chat model alignment, instruction tuning, or text data curation at scale.
• Proficiency with PyTorch, Hugging Face, and modern language model architectures.

Nice to have

• Experience delivering applied ML projects to external customers with measurable outcomes.
• Familiarity with inference optimization frameworks such as vLLM, SGLang, or TensorRT.
• Experience building reusable ML tooling or evaluation infrastructure.

Benefits

• Competitive base salary plus equity
• Unlimited PTO
• Company-wide Refill Days
• Comprehensive health coverage
• Paid leave for pregnancy, parenting, medical needs, and caring for family

About the company

Spun out of MIT CSAIL, Liquid AI builds general-purpose AI systems that run efficiently across deployment targets. They partner with enterprises across consumer electronics, automotive, life sciences, and financial services.