Member of Technical Staff – Post-Training, Reinforcement Learning, Generalization

Cohere

. Train large language models with reinforcement learning .

Posted 10/14/2026full-timeRemote • United StatesLead💰 CA$295,000 - CA$535,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in training large language models using reinforcement learning techniques, with a strong focus on generalization, robustness, and data quality assessment. Proficient in designing and analyzing experiments to optimize model training outcomes and ensure reproducibility.

Highest-signal resume keywords

Reinforcement LearningLarge Language Models (LLMs)PPODistributed TrainingData Quality Principles

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Training Large Language ModelsReinforcement Learning TechniquesGeneralization and Robustness ResearchExperimental Design and AnalysisReward DesignBenchmarking OverfittingTraining Dynamics DiagnosisProduction-Model Training RecipesData AssessmentClean Ablations

Soft Skills

Excellent Communication Skills

Tools & Technologies

JAXPyTorchFSDPMegatron

Industry Keywords

Reinforcement Learning from Human Feedback (RLHF)Reward HackingTask DiversityCurriculaRegularization

Tech Stack

Tools & technologies

PyTorch

About the role

Key responsibilities & impact

Train large language models with reinforcement learning
Develop methods that improve generalization beyond the training distribution
Design training recipes, environments, and evaluations to assess learned skills
Design, run, and analyze large-scale RL post-training experiments, including RLHF and RL from verifiable rewards
Research reward design, environment and task diversity, curricula, and regularization
Build held-out evaluations for unseen tasks, domains, and formats
Detect reward hacking and benchmark overfitting
Diagnose training dynamics and failure modes, including instability, reward over-optimization, and capability regressions
Turn successful research into robust, reproducible production-model training recipes
Collaborate with post-training data infrastructure, evaluation, and pre-training teams

Requirements

What you’ll need

Strong research and software engineering skills, with hands-on experience training LLMs
Experience applying reinforcement learning to LLMs, such as PPO, GRPO, RLHF, or RLVR, ideally at scale
Track record of work on generalization, robustness, or distribution shift through publications or shipped models
Rigorous experimental practice, including clean ablations, careful controls, and sound conclusions from noisy results
Experience with distributed training, such as JAX, PyTorch, FSDP, or Megatron, is a plus
Excellent communication skills
Deep understanding of data quality principles and best practices
Willingness to dive deep into data and assess dataset quality and impacts on model training outcomes

Benefits

Comp & perks

Offers equity
Weekly lunch stipend of $75/£75 or equivalent in local currency
Full health and dental benefits
Separate budget for mental health
RRSP matching, 401K, Pension Scheme
100% parental leave top-up for up to 6 months, for either parent
Annual arts and culture, fitness/wellness, quality time, and workspace improvement benefits
Education and learning stipend for conferences, courses, and coaching
6 weeks of paid vacation (30 working days)
Budget for traveling to other offices if remote
Annual company offsite
Daily lunch program, snacks, and regular community and social events for office-based employees
Co-working benefit for employees not near an office
$500 home office stipend