
Research Engineer - RL & LLM Post-Training
Paris
Wigi highlights
4+ years, currently working as Mid-level Research Engineer
Delivered a PoC for complex electrical board design
Works on large-scale LLM post-training for an SRE agent task
In a previous role, led the internal Reinforcement Learning library, standardizing SOTA RL algorithms for distributed and scalable deployment across diverse client projects, and implemented and optimized state-of-the-art model-free and model-based RL algorithms and inference search strategies, leveraging modern network architectures like Transformers.
They also implemented state-of-the-art Deep Learning models (nnUnet, probabilistic U-Net, transformers-based architecture) with Python, Pytorch, Hydra for segmentation of MRI medical images of infarcted hearts. Separate work involved implementing state-of-the-art Curriculum Learning methods for deep reinforcement learning for the bin packing problem.
Available in 2 weeks
Ready to start in 2 weeks. Interview now. Actively looking.
Skills
Work experience
Unlocks when they connect with you.
- certifications· 2
- education· 3
Similar available AI Research & Applied Scientists
View all- Research Scientist / GNN & Machine Learning Algorithms · Seattle, WA · 8 Yrs Exp · Remote · $11,000/mo
- Data Scientist and Applied AI Researcher · Singapore · 7 Yrs Exp · Hybrid · $7,000/mo
- Deep Learning Researcher (C++, Python) · Edinburgh, UK · 4 Yrs Exp · Remote · $9,000/mo
- Researcher | Image Classsification & Deep Learning · Italy · 10+ Yrs Exp · Hybrid · $6,800/mo
- Computational Physics Research Engineer · Aachen, Germany · 10+ Yrs Exp · Remote · $7,800/mo