Staff ML Engineer: Agentic AI Platform & Guardrails
Robinhood
Stand out for this role — generate a tailored resume and cover letter in about a minute.
Benefits offered by this job
Job summary
Robinhood is building the AI Platform & Agentic Apps team to power increasingly capable agents that act in real time within a regulated financial environment. The Staff ML Engineer will anchor the platform, design the agent harness, and ensure safe, scalable operation across internal and customer-facing agents.
The role emphasizes architecture reviews, mentorship, and a data-driven stance on deciding what to ship, with close collaboration with product and infrastructure teams in a fast-moving
Qualifications
- 10+ years of experience as a Machine Learning Engineer or ML-focused software engineer.
- Strong Python and distributed-systems fundamentals.
- Hands-on experience shipping LLM-powered systems to production at scale.
- Experience building agentic systems end to end on frontier models.
Responsibilities
- Design and build the core of Robinhood's agent harness - orchestration and memory management for scalable platform.
- Ship agentic applications end to end on the harness and bring learnings back to the platform.
- Build trajectory-level evaluation systems to score reasoning and actions of agents.
- Architect action guardrails including permission models and sandboxing.
- Make evals and guardrails products for other teams with SDKs and production tracing.
- Set technical bar via architecture and code reviews and mentor engineers.
Skills
Education
Tools
Job description
Robinhood is building the AI Platform & Agentic Apps team to power increasingly capable agents that act in real time within a regulated financial environment. The Staff ML Engineer will anchor the platform, design the agent harness, and ensure safe, scalable operation across internal and customer-facing agents.
The role emphasizes architecture reviews, mentorship, and a data-driven stance on deciding what to ship, with close collaboration with product and infrastructure teams in a fast-moving
'/%3e%3cpath%20d='M101.744%2012.4726L102.894%2016.1947L99.0021%2013.2201L101.744%2012.4726ZM105.3%208.40937H100.488L99.0026%203.59473L97.5116%208.41047L92.7%208.40385L96.5965%2011.3834L95.1055%2016.1942L99.0021%2013.2196L101.408%2011.3834L105.3%208.40992V8.40937Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_5593_1381'%20x1='90'%20y1='9.44471'%20x2='99'%20y2='9.44471'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%2300AD70'/%3e%3cstop%20offset='0.998594'%20stop-color='%2300B67A'/%3e%3cstop%20offset='1'%20stop-color='%23DCDCE6'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e){kind=small}
