Applied Research Intern

Mountain ViewinternshipOn SiteentryH1B: no

Nexttoken Applied Research Intern at Nexttoken focusing on post-training models and evaluation systems. Responsible for building evaluation suites, verifiers, reward models, and conducting end-to-end post-training experiments.

Responsibilities

Build evaluation suites from production traces
Develop verifiers and reward models from human corrections and outcomes
Conduct post-training experiments including hypothesis, data, SFT/DPO/RL runs, ablations, analysis, and write-ups
Create RL environments and agentic harnesses for specialized workflows
Reproduce and translate recent post-training, reasoning, and agent papers into the stack

Qualification

Strong empirical ML backgroundRigorous about evaluationComfortable in messy production dataBias to shipPublications or OSS in post-trainingExperience with verifier models

Required

Currently a student (BS / MS / PhD) in CS, ML, or an adjacent field, or recently graduated.
Strong empirical ML background. You've run post-training or RL experiments on LLMs and can explain what worked, what didn't, and why.
Rigorous about evaluation. You can spot a benchmark that lies and design one that doesn't.
Comfortable in messy production data. Real traces, not curated datasets, are your raw material.