Lead research engineering efforts to improve AI model capabilities through data pipelines, training environments, and reinforcement learning. Design, build, and evaluate data generation, environment, and post‑training systems with rigorous experimental methodology. Collaborate directly with researchers and engineers to identify gaps and deliver measurable model improvements.
Key Highlights
Develop end‑to‑end data pipelines and synthetic training environments.
Run reinforcement learning experiments and post‑training optimizations.
Own the experimental loop from hypothesis generation to reproducible evaluation.
Key Responsibilities
Build high‑quality data pipelines and develop systems for generating, curating, and validating training data.
Design and implement reliable multi‑step training environments with reproducible execution and useful feedback.
Establish supervised baselines, run reinforcement learning experiments, and investigate effects of data, rewards, and optimization choices.
Create trustworthy evaluations, design graders and held‑out tests, and detect reward hacking or data contamination.
Inspect model failures, formulate testable hypotheses, and conduct controlled ablations to guide subsequent experiments.
Develop tooling that ensures results are reproducible and easy to inspect.
Technical Skills Required
Python
Reinforcement Learning
PyTorch
Benefits & Perks
Comprehensive health, dental, and vision coverage
Flexible PTO
Relocation support
Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.
Nice to Have
Experience building RL environments used by other researchers
Demonstrated improvement of model capabilities through data quality enhancements
Successfully taking post‑training experiments from prototype to reliable production systems
Strong project, research, or open‑source contributions showcasing depth of understanding
Job Description
Sonder is an applied AI lab building models that learn how people work.We bring research, engineering, and design together to build useful personal AI, with privacy and efficiency at the core. We are building our early team in New York.The RoleWe are looking for a research engineer to improve model capabilities through better data, training environments, and reinforcement learning.You will work across data generation, environment design, and post-training, with ownership from an initial hypothesis to a measured improvement in model behavior. The work calls for strong engineering, careful experimentation, and judgment about what is worth pursuing.
Want the full job description?
Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn
This is a short excerpt. All rights to the full description belong to its original publisher.
