Research Scientist

The role

You will research novel approaches to optimize construction, capital allocation, and security operations using AI. You will build simulation environments and deploy models that inform decisions across a fleet of nuclear power plants.

What you will do

• Translate complex operational processes into well-defined research problems
• Build simulation environments for construction scheduling, portfolio sequencing, and security operations
• Design rigorous experiments and maintain reproducible codebases
• Develop models to optimize construction scheduling across multiple sites
• Design approaches for dynamic rescheduling to adapt to disruptions
• Build models to inform site development sequencing and capital allocation
• Develop approaches for uncertainty quantification in key inputs
• Build models for alert prioritization, anomaly detection, and patrol scheduling
• Design human-in-the-loop systems for shared decision authority
• Collaborate with engineering to deploy, monitor, and update models in production

Required qualifications

• PhD in Computer Science, Machine Learning, Operations Research, Economics, Applied Mathematics, or a closely related quantitative field, or MS with a demonstrable track record of independent research
• Hands-on experience implementing and evaluating deep RL algorithms
• Fluency in policy gradient methods (PPO, TRPO, SAC), value-based approaches (DQN variants, IQL), and the tradeoffs between model-free and model-based RL
• Experience building RL training environments
• Ability to translate complex real-world operational processes into tractable MDP formulations
• Production-quality Python
• Deep learning frameworks (PyTorch)
• Version control, testing, and reproducibility practices
• Ability to operate in a fast-moving environment

Nice to have

• Offline / Batch RL (IQL, CQL, TD3+BC, Decision Transformer)
• Combinatorial Optimization + ML (Graph neural networks, neural combinatorial optimization, or hybrid learned/exact solver approaches)
• Multi-Agent RL (MADDPG, QMIX, MAPPO)
• Stochastic / Robust Optimization (CVaR-constrained RL, distributionally robust MDPs, or chance-constrained programming)
• Production RL Deployment (monitoring and retraining RL systems)
• Domain Exposure (Construction project management, infrastructure operations, energy industry, electricity markets, nuclear power, industrial control systems, or physical/cyber security)
• Game Theory
• Behavioral Science
• Research Program Leadership (2-5 years of post-PhD research experience)
• Publication Track Record (NeurIPS, ICML, ICLR, AAMAS, or equivalent)

Benefits

• Competitive compensation packages
• 401k with company match
• Medical, dental, vision plans
• Generous vacation policy
• Holidays

About the company

The Nuclear Company is an AI tech-enabled startup in the nuclear and energy space. They use a design-once, build-many model to accelerate the deployment of nuclear energy.