Member of Technical Staff - Post Training, Applied

What you'll do

• Lead customer post-training projects from requirements and specifications through model delivery and evaluation.
• Design data generation, filtering, quality assessment, and task-specific evaluations for text models.
• Run fine-tuning and preference-alignment workflows and build reusable tooling for future engagements.

What they ask for

• Hands-on experience with data generation and evaluation for LLM post-training.
• Experience training or fine-tuning models using SFT, instruction tuning, RLHF, DPO, or similar preference-alignment methods.
• Strong intuition for text data quality and evaluation design, plus text-specific post-training workflow experience.
• Proficiency with the open-source ML ecosystem (Hugging Face, PyTorch) and modern model architectures.

Nice to have

• Experience delivering applied ML work to external customers with measurable outcomes.
• Familiarity with inference optimization frameworks (vLLM, SGLang, TensorRT), or experience building reusable ML tooling or evaluation infrastructure.

Tools

Hugging Face, PyTorch, SFT, instruction tuning, RLHF, DPO, vLLM, SGLang

AI focus

Applied post-training of text models, including data generation and curation, fine-tuning, preference alignment, evaluation, and customer delivery.