Staff Software Engineer, Agentic, Optimization, Recursive Self-Improvement
Google · Posted Nov 5, 2026
- Mountain View, California, United States
- On-site
- Full-time · Staff
- $207K–$300K per year
- 8+ years
Help set and execute technical direction for autonomous, closed-loop agentic systems that continuously optimize, compress, and modularize system instructions and agent trajectories.
Compensation
US: $207000 - $300000 (USD) + 20% bonus target + equity + benefits
Responsibilities
- Partner with senior leads to architect closed-loop RSI pipelines that autonomously diagnose failure modes, refine instructions/trajectories, synthesize targeted training/eval data.
- Investigate and build automated multi-agent systems that audit, compress, and de-conflict complex model context.
- Bridge inference-time context engineering with model post-training (SFT/RL) to distill complex rules into model weights.
- Advance automated optimization methods for production multimodal and reasoning systems.
- Help define the multi-quarter roadmap across Engineering and Research teams, establishing rigorous automated evaluation gates.
Requirements
- Bachelor’s degree or equivalent practical experience
- Nice to have: data structures and algorithms
- Nice to have: technical leadership
- Nice to have: Recursive Self-Improvement
- Nice to have: automated prompt