Member of Technical Staff – Post‑Training Applied

About the role

Liquid‑AI is looking for a Member of Technical Staff to own end‑to‑end post‑training work for text workloads. You will bridge enterprise customer requirements with model delivery, adapting Liquid Foundation Models for large‑scale deployments.

Key responsibilities

• Act as technical owner for enterprise post‑training engagements involving text models.
• Translate customer requirements into concrete specifications and workflows.
• Design and execute data generation, filtering, and quality assessment for text corpora.
• Run supervised fine‑tuning, instruction tuning, RLHF, DPO, and other preference‑alignment pipelines.
• Create task‑specific evaluations, interpret results, and iterate on model performance.
• Build reusable tooling and workflows to accelerate future customer projects.

Required profile

• Hands‑on experience with data generation and evaluation for LLM post‑training.
• Proven ability to own projects from scoping through delivery and evaluation.
• Pragmatic mindset focused on model quality and customer outcomes.
• Clear communicator who can translate between customer needs and internal teams.

Required skills

• Large Language Model post‑training workflows.
• Supervised fine‑tuning (SFT), instruction tuning, RLHF, DPO.
• Data generation, filtering, and quality assessment for text data.
• Open‑source ML ecosystem: Hugging Face, PyTorch.
• Inference optimization frameworks: vLLM, SGLang, TensorRT.
• Building reusable ML tooling and evaluation infrastructure.