Inception

Member of Technical Staff, Reinforcement Learning

San Mateo, USA · Staff+

Sponsorship not specifiedDetected 134 days ago

AlgorithmsMachine LearningDeep LearningPyTorchNLPLLMsResearch

About the role

We seek experienced scientists and engineers with deep expertise in post-training large language models through reinforcement learning.

Design, develop, and optimize RL training pipelines (PPO, DPO, RLHF, and novel approaches) for diffusion-based LLMs.
Build and iterate on reward models, reward shaping strategies, and evaluation of reward quality.
Implement innovative approaches for fine-tuning and scaling generative AI models.
Research and implement techniques for controlled text generation and constraint satisfaction.

Work on data preprocessing pipelines, model evaluation, and alignment to enterprise use cases.
Improve training stability, efficiency, and reproducibility of RL workloads.
BS/MS/PhD in Computer Science or a related field (or equivalent experience).
At least 2 years of experience working on ML projects in PyTorch (or equivalent), preferably in a research lab or engineering role.
Familiarity with training and inference in diffusion models.
Preferred Skills Extensive experience training transformer-based language models from scratch.
Knowledge of advanced training techniques (mixed precision, gradient accumulation, etc.).
Experience with LLM serving frameworks like vLLM, SGLang, or TensorRT.

Excellent familiarity with transformers and core LLM concepts (autoregressive pretraining, instruction tuning, in-context learning, KV caching).
Hands-on experience with reinforcement learning from human feedback (RLHF), PPO, DPO, or related post-training methods.
Experience training deep learning models at scale in distributed computing environments.
Experience designing and implementing reward models or preference learning systems.

This listing is sourced directly from Inception's careers page and normalized into a canonical job model.