Machine Learning Engineer, Reinforcement Learning
XenonStack · Mohali, India ·
- Category
- ML ai
- Experience
- 2+ years
- Company size
- 51-200
XenonStack · Mohali, India ·
XenonStack is a Data and AI Foundry for Agentic Systems, enabling enterprises to design, deploy, operate, and scale intelligent agents across digital and physical environments.
We build enterprise-grade platforms across the agentic stack:
Our mission is to accelerate the world’s transition to AI + Human Intelligence by making agentic systems reliable, responsible, and enterprise-ready.
We are seeking an Machine Learning Engineer, Reinforcement Learning (Specialized in Reinforcement Learning) with 2–5 years of experience in applying RL to enterprise-grade systems. This role involves designing and deploying adaptive AI agents that continuously learn, optimize decisions, and evolve in dynamic environments.
You’ll work at the intersection of RL research, agentic orchestration, and real-world enterprise workflows — building agents that do more than automate, but truly reason, adapt, and improve over time.
Reinforcement Learning Development
Design, implement, and train RL algorithms (PPO, A3C, DQN, SAC) for enterprise decision-making tasks.
Develop custom simulation environments to model business processes and operational workflows.
Experiment with reward function design to balance efficiency, accuracy, and long-term value creation.
Agentic AI System Design
Build production-ready RL-driven agents capable of dynamic decision-making and task orchestration.
Integrate RL models with LLMs, knowledge bases, and external tools for agentic workflows.
Implement multi-agent systems to simulate collaboration, negotiation, and coordination.
Deployment & Optimization
Deploy RL agents on cloud and hybrid infrastructures (AWS, GCP, Azure).
Optimize training and inference pipelines using distributed computing frameworks (Ray RLlib, Horovod).
Apply model optimization techniques (quantization, ONNX, TensorRT) for scalable deployment.
Evaluation & Monitoring
Develop pipelines for evaluating agent performance (robustness, reliability, interpretability).
Implement fail-safes, guardrails, and observability for safe enterprise deployment.
Document processes, experiments, and lessons learned for continuous improvement.
Technical Skills
2–5 years of hands-on experience with Reinforcement Learning frameworks (Ray RLlib, Stable Baselines, PyTorch RL, TensorFlow Agents).
Strong programming skills in Python; proficiency with PyTorch / TensorFlow.
Experience designing and training RL algorithms (PPO, DQN, A3C, Actor-Critic methods).
Familiarity with simulation environments (Gymnasium, Isaac Gym, Unity ML-Agents, custom simulators).
Experience in reward modeling and optimization for real-world decision-making tasks.
Knowledge of multi-agent systems and collaborative RL is a strong plus.
Familiarity with LLMs + RLHF (Reinforcement Learning with Human Feedback) is desirable.
Exposure to cloud platforms (AWS/GCP/Azure), containers (Docker, Kubernetes), and CI/CD for ML.
Professional Attributes
Strong analytical and problem-solving mindset.
Ability to balance research depth with practical engineering for production-ready systems.
Collaborative approach, working across AI, data, and platform teams.
Commitment to Responsible AI (bias mitigation, fairness, transparency).
At XenonStack, we believe in shaping the future of intelligent systems. We foster a culture of cultivation built on bold, human-centric leadership principles, where deep work, simplicity, and adoption define everything we do.
Our Cultural Values
Agency – Be self-directed and proactive.
Taste – Sweat the details and build with precision.
Ownership – Take responsibility for outcomes.
Mastery – Commit to continuous learning and growth.
Impatience – Move fast and embrace progress.
Customer Obsession – Always put the customer first.
Our Product Philosophy
Obsessed with Adoption – Making AI agents accessible and enterprise-ready.
Obsessed with Simplicity – Turning complex RL + agentic challenges into intuitive, reliable systems.
Be part of our mission to reimagine adaptive, enterprise-grade AI agents with Reinforcement Learning and accelerate the world’s transition to AI + Human Intelligence.