Tech and design

Staff Research Scientist - Post-Training for Agents

DatadogNew York, New York, USA; Pittsburgh, Pennsylvania, USA

• Pay$320,000–400,000 per year
• WhereNew York, New York, USA; Pittsburgh, Pennsylvania, USA
• ExperienceExperienced
• PerksHealthcare, Dental, Parental planning, Mental health benefits
• Skills and toolsReinforcement learning, Agent training, Post-training methods, Simulated environments, Synthetic data generation, Evaluation frameworks, Generative modeling, Model development, Training loops
• You’ll needPhD or equivalent experience
• ReferenceRef. 6039
• In the paper untilThu 19 Nov

About the job

$320–400k a year. Hands-on research in post-training, reinforcement learning, simulated environments, synthetic data generation, and agent evaluation. PhD in computer science, machine learning, or a related field, or equivalent experience. Healthcare, dental, parental planning, and mental health benefits.

This is our short summary. Read the full posting on careers.datadoghq.com.

Found on careers.datadoghq.com. Not placed by the employer; applications go to the original posting.