Inception Labs
Member of Technical Staff, Reinforcement Learning
San Mateo, United States · On-site · Staff · Full-time · Posted Mar 10, 2026
- Experience
- At least 2 years of ML project experience; no stated alternatives.
- Education
- BS/MS/PhD in Computer Science or a related field, or equivalent experience.
About the job
Design and build reinforcement-learning post-training systems that align Inception’s diffusion-based large language models with human intent and enterprise needs.
What you'll do
- Design and optimize RL training pipelines, including PPO, DPO, RLHF, and novel methods.
- Develop reward models and reward-shaping strategies, and evaluate reward quality.
- Build fine-tuning, evaluation, and data-preprocessing systems; improve training stability, efficiency, and reproducibility.
What they ask for
- At least 2 years of experience working on ML projects in PyTorch or equivalent.
- Excellent familiarity with transformers and core LLM concepts.
- Hands-on experience with RLHF, PPO, DPO, or related post-training methods.
- Familiarity with training and inference in diffusion models and training deep-learning models at scale in distributed computing environments.
Nice to have
- Extensive experience training transformer-based language models from scratch or designing reward models/preference-learning systems.
- Knowledge of advanced training techniques, optimization theory, neural network architecture design, or LLM serving frameworks.
Tools
PyTorch, PPO, DPO, RLHF, transformers, vLLM, SGLang, TensorRT
AI focus
Post-training diffusion LLMs with reinforcement learning; reward modeling, alignment, controlled text generation, constraint satisfaction, and model evaluation.
Model-written summary · the original posting is authoritative