Member of Technical Staff
Plato
Member of Technical Staff
Plato
Delivers reproducible AI training environments
Plato is an applied research lab building the foundational infrastructure to train specialized AI agents.
We turn real-world data streams into high-fidelity simulated environments that generate the training signal needed to make capable models. Our work supports frontier labs, hyperscalers, and enterprises building AI systems for complex, high-stakes work.
Today, only a handful of players can train models for capable work. Compute and algorithms are rapidly commoditizing, but reinforcement learning data remains the bottleneck. Plato is changing that by automatically scaling training environments from proprietary real-world data.
Work with the frontier: You will be the day-to-day partner to research teams at the world's top AI labs, running the environment projects that shape how their next models are trained and evaluated.
Real ownership: You run projects end to end, from a lab's first spec to final delivery, with a direct line to the founders.
High-stakes execution: Tight timelines, demanding researchers, and a quality bar where one leaky reward or brittle verifier can sink a project. Every project you deliver well grows Plato's work with that lab.
Room to grow: You start as an individual contributor running projects. Strong performers move up to running multiple projects and leading the team of project leads that follows.
A great environment is only as good as its delivery.
Technical Acccount Manager - Frontier Labs is a hands-on operations role. You will own Plato's environment and data projects for 1-2 frontier labs from start to finish: turning a lab's research needs into a clear spec, coordinating the engineers and domain experts who build the tasks and verifiers, holding the quality bar, and keeping the customer informed and confident at every step. The trust you build with each lab is what drives Plato's next project with them.
Own Delivery: Run projects from customer spec to final delivery. Set milestones, track throughput and cost, and hit timelines that often move fast.
Manage Lab Relationships: Serve as the primary day-to-day contact for research teams at leading AI labs. Provide consistent, transparent reporting, anticipate what they need next, and spot opportunities to expand the work.
Coordinate Experts at Scale: Source, vet, onboard, train and manage the domain experts and contributors who build tasks, environments and reviews, sometimes ramping large groups on a few days' notice.
Hold the Quality Bar: Build the review processes, incentives and workflows that raise quality, throughput and cost-efficiency. Work with engineering and research to catch reward hacking, leaky rewards and brittle verifiers before the customer does.
Run the Daily Rhythm: Lead daily internal syncs on project health, flag risks early, and turn customer feedback into better process and product.
Track Record: 2 + years at a top research lab, or AI native startup company or another operationally intense AI environment, with complex research and data projects delivered on time.
Client Presence: Comfortable working directly with senior, technical and high-profile clients and owning the relationship.
Analytical and Clear: Strong analytical skills, and you communicate progress and problems plainly, in writing and live.
Process Builder: You enjoy optimizing workflows and running execution at scale.
High Ownership: You stay responsive when a project needs it, including evenings and weekends during crunch periods.
Bay Area Based: Able to work in person in San Francisco 5x a week (financial district)
Experience running data, annotation, evaluation or RL environment projects for AI labs, at an AI data company or inside a lab.
A technical degree in a field such as Data Science or similar, or strong familiarity with Python, SQL and how models are trained and evaluated.
Experience managing large distributed contractors or expert workforces.
Former founder or early startup employee.
Hands-on experience with LLMs, agents or evaluation tools.
Plato creates datasets and simulated environments to train and evaluate AI web agents. It produces static, reproducible environments from human demonstrations, providing labs and agent developers a controlled way to benchmark and reinforce-behavior learning on real-world web tasks. Unlike other providers, Plato focuses on supplying the data and virtual “gyms” that power modern AI progress in reinforcement learning. Its goal is to help advance AI by making reliable, testable environments and benchmarks for web-based tasks.
Explore more opportunities at Plato