Naïve Verified
Founding Member of Technical Staff — RL
Mountain View, CAOnsiteFull TimeStaff$190,000–$225,000 /yrPosted 1 month agoHidden Gem · YC Startup
Required skills
- Python
- agents
- evals
- RL environments
- tool use
- long-horizon tasks
- LLM failure modes
- rigorous experiments
- production systems
- autonomous company blueprints
Nice to have
- RL
- post-training
- browser agent
- coding agent
- computer-use agent
- benchmarks
Role summary
Naive is seeking a Founding Member of Technical Staff specializing in Reinforcement Learning (RL) to build autonomous company systems and agent environments. This role involves turning complex business workflows into reproducible agent systems, designing experiments and benchmarks, and improving agent performance. The ideal candidate will have strong Python and research-engineering skills, experience building agents or RL environments, and a deep understanding of tool use, long-horizon tasks, and LLM failure modes. This is a unique opportunity to earn significant equity in a fast-growing Series A company.
## About Naive
Naive is building autonomous companies: agent systems capable of operating real businesses end to end.
We release autonomous company templates and benchmarks, alongside a studio—where users can deploy and operate these systems. Our infrastructure platform, Vetta, powers long-running, high-volume agent workloads.
We’ve raised $28.5M from Nexus Venture Partners, Y Combinator, Zetta Venture Partners, Liquid 2 and leading operators.
## The Role
Build real-world agent environments, benchmarks and autonomous company blueprints—and make Vetta the best-performing agent within them. Accordingly, as a founding MTS member, you have the chance to earn significant equity in a fast growing Series A company.
## What You’ll Do
* Turn complex business workflows into reproducible agent environments
* Design tasks, rewards, evals and benchmarks that measure real outcomes
* Build production-ready autonomous company blueprints
* Run experiments, analyze failures and improve agent performance
* Develop training data and optimization loops from agent trajectories
* Publish credible benchmarks, technical reports and demos
## Must-Haves
* Strong Python and research-engineering ability
* Experience building agents, evals or RL environments
* Deep understanding of tool use, long-horizon tasks and LLM failure modes
* Ability to design rigorous experiments and ship production systems
* High agency and comfort working on ambiguous 0→1 problems
## Nice-to-Haves
* RL or post-training experience
* Browser, coding or computer-use agent experience
* Experience publishing benchmarks or technical research
* Familiarity with distributed agent infrastructure
_P.S. If you’ve made it to the bottom of this listing and are serious about every point on this role, send Sean a LinkedIn connect with a note._
Naive is building autonomous companies: agent systems capable of operating real businesses end to end.
We release autonomous company templates and benchmarks, alongside a studio—where users can deploy and operate these systems. Our infrastructure platform, Vetta, powers long-running, high-volume agent workloads.
We’ve raised $28.5M from Nexus Venture Partners, Y Combinator, Zetta Venture Partners, Liquid 2 and leading operators.
## The Role
Build real-world agent environments, benchmarks and autonomous company blueprints—and make Vetta the best-performing agent within them. Accordingly, as a founding MTS member, you have the chance to earn significant equity in a fast growing Series A company.
## What You’ll Do
* Turn complex business workflows into reproducible agent environments
* Design tasks, rewards, evals and benchmarks that measure real outcomes
* Build production-ready autonomous company blueprints
* Run experiments, analyze failures and improve agent performance
* Develop training data and optimization loops from agent trajectories
* Publish credible benchmarks, technical reports and demos
## Must-Haves
* Strong Python and research-engineering ability
* Experience building agents, evals or RL environments
* Deep understanding of tool use, long-horizon tasks and LLM failure modes
* Ability to design rigorous experiments and ship production systems
* High agency and comfort working on ambiguous 0→1 problems
## Nice-to-Haves
* RL or post-training experience
* Browser, coding or computer-use agent experience
* Experience publishing benchmarks or technical research
* Familiarity with distributed agent infrastructure
_P.S. If you’ve made it to the bottom of this listing and are serious about every point on this role, send Sean a LinkedIn connect with a note._
