Agentic AI Engineer - RL

XenonStack; Mohali; On-site; INR 1,200,000 - 2,800,000; Full time

Job summary

XenonStack is the fastest-growing Data and AI Foundry for Agentic Systems, enabling real-time, intelligent business insights and enterprise-grade AI agents. We build Akira AI and NexaStack AI foundations to empower organizations to reason, perceive, and act with AI.

Join as Agentic AI Engineer (Reinforcement Learning) with 2–5 years of experience to design, train, and deploy RL agents, build custom simulators, integrate with LLMs, and orchestrate multi-agent workflows across cloud and hybrid

Qualifications

• 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 is desirable.
• Exposure to cloud platforms (AWS/GCP/Azure), containers (Docker, Kubernetes), and CI/CD for ML.

Responsibilities

• 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).
• 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.

Skills

Reinforcement Learning

Python

PyTorch

TensorFlow

RL frameworks

Simulation design

LLMs integration

Multi-agent systems

Cloud platforms

Docker

Kubernetes

RLHF

Education

Bachelor’s degree in CS/AI

Tools

Gymnasium

Isaac Gym

Unity ML-Agents

Ray RLlib

Stable Baselines

PyTorch RL

TensorFlow Agents

Docker

Kubernetes

Job description

XenonStack is the fastest-growingData and AI Foundry for Agentic Systems, enabling people and organizations to gainreal-time and intelligent business insights.

We deliver innovation through:

Akira AI – Building Agentic Systems for AI Agents

NexaStack AI – Inference AI Infrastructure for Agentic Systems

Our mission is to accelerate the world’s transition toAI + Human Intelligence, combining reasoning, perception, and action to createenterprise-ready AI agents.

THE OPPORTUNITY

We are seeking anAgentic AI Engineer (Specialized in Reinforcement Learning)with2–5 years of experiencein applying RL to enterprise-grade systems. This role involves designing and deployingadaptive AI agentsthat continuously learn, optimize decisions, and evolve in dynamic environments.

You’ll work at the intersection ofRL research, agentic orchestration, and real-world enterprise workflows— building agents that do more than automate, but trulyreason, adapt, and improve over time.

JOB ROLES AND RESPONSIBILITIES

• Design, implement, and trainRL algorithms(PPO, A3C, DQN, SAC) for enterprise decision-making tasks.
• Developcustom simulation environmentsto model business processes and operational workflows.
• Experiment withreward function designto balance efficiency, accuracy, and long-term value creation.
• Agentic AI System Design
  • Buildproduction-ready RL-driven agentscapable of dynamic decision-making and task orchestration.
  • Integrate RL models withLLMs, knowledge bases, and external toolsfor agentic workflows.
  • Implementmulti-agent systemsto simulate collaboration, negotiation, and coordination.
• Deployment & Optimization
  • Deploy RL agents oncloud and hybrid infrastructures(AWS, GCP, Azure).
  • Optimize training and inference pipelines usingdistributed computing frameworks(Ray RLlib, Horovod).
• Evaluation & Monitoring
  • Develop pipelines forevaluating agent performance(robustness, reliability, interpretability).
  • Implementfail-safes, guardrails, and observabilityfor safe enterprise deployment.
• Document processes, experiments, and lessons learned for continuous improvement.

SKILLS REQUIREMENTS

• Technical Skills
  • 2–5 years of hands‑on experience withReinforcement Learning frameworks(Ray RLlib, Stable Baselines, PyTorch RL, TensorFlow Agents).
  • Strong programming skills inPython; proficiency withPyTorch / TensorFlow.
  • Experience designing and trainingRL algorithms(PPO, DQN, A3C, Actor‑Critic methods).
  • Familiarity withsimulation environments(Gymnasium, Isaac Gym, Unity ML-Agents, custom simulators).
  • Experience inreward modeling and optimizationfor real‑world decision‑making tasks.
  • Knowledge ofmulti‑agent systemsand collaborative RL is a strong plus.
  • Familiarity withLLMs + RLHF (Reinforcement Learning with Human Feedback)is desirable.
  • Exposure tocloud platforms (AWS/GCP/Azure), containers (Docker, Kubernetes), and CI/CD for ML.
• Professional Attributes
  • Strong analytical and problem‑solving mindset.
  • Ability to balanceresearch depthwithpractical engineeringfor production‑ready systems.
  • Collaborative approach, working across AI, data, and platform teams.
  • Commitment toResponsible AI(bias mitigation, fairness, transparency).

XENONSTACK CULTURE – JOIN US & MAKE AN IMPACT!

At XenonStack, we believe inshaping the future of intelligent systems. We foster aculture of cultivationbuilt on bold, human-centric leadership principles, wheredeep work, simplicity, and adoptiondefine 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 toreimagine adaptive, enterprise-grade AI agentswith Reinforcement Learning and accelerate the world’s transition toAI + Human Intelligence.

WHY SHOULD YOU JOIN US?

1. Agentic AI Product Company

   Buildenterprise-grade AI platformspowered by Machine Learning, Generative AI, and Agentic Systems. From Vision AI to Inference Infrastructure, you’ll shape products that redefine enterprise AI adoption.

2. A Fast-Growing Category Leader

   XenonStack is one of thefastest-growing Data and AI Foundries, setting benchmarks in how businesses deploy and scale AI agents with platforms likeAkira AI, NexaStack, and Vision AI.

3. Career Mobility & Growth

   Move between roles and functions — fromAI Engineering to Product Marketing or AgentOps— and craft a career that grows with your aspirations.

4. Global Exposure

   Work withFortune 500 enterprises, BFSI leaders, and global innovators, delivering real-world impact across industries and geographies.

5. Create Real Impact

   Contribute from day one. Even junior team members work onmission-critical product featuresthat go into production.

6. Culture of Excellence

   Our values —Agency, Taste, Ownership, Mastery, Impatience, and Customer Obsession— empower you to push boundaries and innovate fearlessly.

7. Responsible AI First

   Join a company that prioritizestrustworthy, explainable, and compliant AI. You’ll contribute toResponsible AI frameworks, ensuring our agentic systems are not just powerful, but also ethical and reliable.