Staff AI Security Engineer - Post-Training & Scale

Armadin; Palo Alto (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Full health, dental, vision

Equity ownership

In-office meals

Haircuts at the office

Conferences & events

401(k), HSA, and FSA plans

Flexible PTO

Job summary

Armadin, based in Palo Alto, is seeking a senior researcher to own the post-training strategy and to translate security research into scalable model capabilities. You will drive fine-tuning, reward modeling, and efficiency benchmarks, ensuring reliability and impact across production environments.

The role requires a PhD or equivalent experience with hands-on SFT, RLHF/RLAIF, and distillation. You will collaborate across teams to push frontier research into practical, enterprise-grade solutions.

Qualifications

• PhD in CS, ML, or related field, or equivalent experience with a strong track record.
• Hands-on experience with SFT, RLHF/RLAIF, DPO, and reward modeling.
• Practical ability to train, fine-tune, and evaluate models and deploy research to production.
• Engineering strength to implement ideas and run them at scale.
• Ability to drive strategy broadly or focus deeply on hard problems as needed.
• Strong collaboration across teams and focus on outcomes.

Responsibilities

• Own Post-Training Strategy: Drive the post-training roadmap (fine-tuning, preference optimization, reward modeling, RL, distillation) to make models more capable, reliable, and aligned.
• Push Efficiency & Evals: Make models serve reliably at scale, and build the benchmarks that measure quality and catch regressions.
• Ground Research in Reality: Turn our security experts’ tradecraft into model capabilities and ship your techniques into production.
• Stay at the Frontier: Track post-training and efficiency research and bring the best ideas in.

Skills

PhD or equivalent

Post-training techniques

Model training & evaluation

Scale engineering

Strategic thinking

Cross-team collaboration

Education

PhD in CS/ML or related field

Job description

Armadin, based in Palo Alto, is seeking a senior researcher to own the post-training strategy and to translate security research into scalable model capabilities. You will drive fine-tuning, reward modeling, and efficiency benchmarks, ensuring reliability and impact across production environments.

The role requires a PhD or equivalent experience with hands-on SFT, RLHF/RLAIF, and distillation. You will collaborate across teams to push frontier research into practical, enterprise-grade solutions.