Applied Research Intern
NextToken
With an account: save jobs, track applications, build tailored resumesAlready have an account? Log in
- Location
- Mountain View, CA
- +1 more location
- Work style
- On-site
- Job type
- Internship
- Posted
- Oct 24
- 2 days ago
Career path
See where this role leads
Jigup maps the next three moves from a job like this one, with the titles and the skills each step asks for.
What you'll do
- You will build evaluation suites and reward models to improve model performance based on production traces.
- You will also conduct end-to-end post-training experiments and develop agentic harnesses for specialized workflows.
What you need
- Candidates must be current students or recent graduates in CS, ML, or an adjacent field with a strong empirical machine learning background.
- You should have experience running post-training or RL experiments on LLMs and a rigorous approach to evaluation.
- Education: a bachelor's degree or a postgraduate degree
Key skills
Machine LearningLLMReinforcement LearningSFTDPORLHFData AnalysisEvaluation DesignPythonAgentic FrameworksModel TrainingEmpirical ResearchProduction SystemsSynthetic DataVerifier Models
Keywords for your resumePro
The words this employer's screening is likely to look for.
This job lists resume keywords
The terms this posting uses, pulled out so you can mirror them in your resume. Jigup Pro members see the list on the job board.
See full description on company page, apply now
Read the full posting here
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.