Applied Research Intern

NextToken; Mountain View (CA); On-site; USD 34,000 - 48,000; Part time

Benefits offered by this job

Publications or OSS in post-training,,

Experience with verifier models

Shipped research into production

Trend awareness

Job summary

NextToken in Mountain View is seeking a student or recent graduate to join our research team as an ML research intern. You will work with real production traces, design evaluation suites, and build reward models to guide post-training improvements.

You''ll run post-training or RL experiments on LLMs, analyze results with numbers, and contribute to deployed workflows. This role emphasizes shipping tangible results and learning through hands-on practice over 12 weeks.

Qualifications

• Currently a student (BS / MS / PhD) in CS, ML, or adjacent field, or recently graduated.
• Strong empirical ML background with hands-on post-training/RL experiments on LLMs.
• Rigorous about evaluation and benchmarking.
• Comfortable working with real production traces.
• Commitment of at least 12 weeks.

Responsibilities

• Evaluation suites built from production traces.
• Verifiers and reward models from corrections and outcomes.
• Post-training experiments end-to-end with data and analysis.
• RL environments and agentic harnesses for workflows.
• Reproducing recent post-training papers and translating them to our stack.

Skills

Empirical ML

RL experiments

LLMs

Experiment design

Production data handling

Education

CS/ML degree candidate or recent graduate

Job description

Sit at the edge of research and production. You'll take a real workflow from a real team, make its failure modes measurable, construct the reward system, and post-train models that beat the frontier baseline on the work that matters. We hire interns who want to be researchers who ship.

What you'll own

• Evaluation suites built from production traces: deciding what to measure, building the graders, and proving they track real quality.

• Verifiers and reward models. Turning human corrections, outcomes, and standards of good work into training signal.

• Post-training experiments end-to-end: hypothesis, data, SFT/DPO/RL runs, ablations, analysis, and the write-up that defends the win with numbers.

• RL environments and agentic harnesses for the workflows we're specializing models for.

• Reproducing recent post-training, reasoning, and agent papers, and translating the ones that work into our stack.

About you

• 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.

• Bias to ship. Your experiments end in a deployed model or a killed hypothesis, not just a doc.

• Available for at least 12 weeks at meaningful intensity.

Bonus

• Publications or OSS in post-training, RL, evals, or agents.

• Experience with verifier models, synthetic data, or RL environments at scale.

• Shipped research into a production system before.

• Strong taste for what the field is over- vs. under-investing in.