Job Title: Reinforcement Learning Engineer — Energy Optimization (1 Position)
About the Job
We are seeking a skilled Reinforcement Learning Engineer to join our team and lead the development of RL-driven solutions for energy optimization across UPS, battery systems, and site-level power management. In this role you will design, implement and deploy RL agents and hybrid control strategies that reduce energy consumption, extend battery life, optimize charge/discharge scheduling, and improve operational resilience. The ideal candidate combines deep ML/RL expertise with practical systems engineering experience and a strong interest in applied energy systems.
Responsibilities
- Research & Development: Design and implement reinforcement learning algorithms (model-free and model-based), multi-objective RL, and hybrid RL/optimization solutions for energy management problems.
- Simulation & Digital Twins: Build, validate and maintain simulation environments and digital twins (Gym-style or custom) that accurately model UPS/battery behavior, load profiles, and grid interactions for agent training and evaluation.
- Data & Feature Engineering: Work with telemetry and sensor data to produce high-quality datasets, features and reward/cost functions; apply time-series analysis and signal processing as needed.
- Training & Evaluation: Train RL agents at scale, tune hyperparameters, perform ablation studies, and establish robust evaluation metrics (safety, reliability, sample-efficiency, interpretability).
- Deployment & MLOps: Productionize models for edge or cloud deployment (on-device inference, containerized services), integrate with device management/OTA systems, and implement CI/CD for ML models.
- Safety & Constraints: Ensure learned policies respect safety, hardware constraints and regulatory requirements (constraint-aware RL, safe exploration, verification testing).
- Cross-functional Collaboration: Work closely with hardware, firmware, product and field teams to integrate RL solutions into real-world products and pilot deployments.
- Documentation & Knowledge Sharing: Produce clear technical documentation, reproducible experiments, and share findings with stakeholders; mentor junior engineers.
Qualifications
- MSc or PhD in Computer Science, Electrical Engineering, Robotics, Control Systems, or related field (or equivalent industry experience).
- 3+ years experience applying machine learning, with at least 1–2 years focused on reinforcement learning or control.
- Strong programming skills in Python and hands-on experience with RL frameworks (e.g., PyTorch, TensorFlow, Stable Baselines, RLlib, Acme).
- Experience building simulation environments (OpenAI Gym, custom simulators), and working with time-series telemetry.
- Familiarity with control theory, optimization, model predictive control (MPC) or hybrid RL+MPC approaches is a strong plus.
- Experience with cloud platforms (AWS/GCP/Azure), Docker, Kubernetes, and MLOps tools for deployment and monitoring.
- Understanding of energy systems, batteries, UPS operation, or power electronics is highly desirable.
- Strong analytical, experimental design and problem-solving skills.
- Excellent communication skills and ability to collaborate across multidisciplinary teams.
What We Offer
- The opportunity to apply advanced RL to real-world energy systems with measurable impact.
- A collaborative, cross-disciplinary team of engineers, product managers and field specialists.
- Competitive compensation and resources for research and pilots.
- Flexibility (remote/hybrid options) and support for professional development.
- Hands-on involvement in pilot deployments and product integrations.
How to Apply
Please submit the following to [HIDDEN TEXT] with subject line 'Reinforcement Learning Engineer — Energy Optimization':
1. CV (max 2 pages)
2. Cover letter (1 page) describing relevant RL/energy experience and why you're excited about this role
3. Links to portfolio, GitHub, publications or projects demonstrating RL/control work (PDF or URLs)
4. Two references (name, role, contact)
Shortlisted candidates may be asked to present a brief technical walkthrough or reproducible experiment. We welcome applications from diverse backgrounds and encourage candidates who combine research rigor with engineering pragmatism to apply.
