Armadin
Member of Technical Staff - Research
Palo Alto · On-site · Staff · Full-time · Posted Jul 3, 2026
- Education
- PhD in CS, ML, or related field, or equivalent experience.
About the job
Drive post-training research and strategy for security models, improve model efficiency and evaluation, and deploy research techniques in production.
What you'll do
- Own the post-training roadmap, including fine-tuning, preference optimization, reward modeling, RL, and distillation.
- Improve reliable model serving at scale and build benchmarks to measure quality and catch regressions.
- Translate security experts’ tradecraft into model capabilities and ship techniques into production.
What they ask for
- PhD in CS, ML, or a related field, or equivalent experience with a strong track record.
- Hands-on experience with SFT, RLHF/RLAIF, DPO, and reward modeling.
- Experience training, fine-tuning, and evaluating models and applying research in practice.
- Ability to implement ideas and run them at scale.
Nice to have
- Publications in top ML venues such as NeurIPS, ICML, ICLR, or ACL.
- Experience with RL, preference optimization, or reward modeling at scale.
Tools
SFT, RLHF/RLAIF, DPO, RL
AI focus
Develop and post-train security models and agents, including fine-tuning, preference optimization, reward modeling, RL, distillation, and evaluation.
Model-written summary · the original posting is authoritative