MLOps Engineer

XenonStack Moments; San Martin Cp3 Hualtaco I; Presencial; PEN 60.000 - 100.000; Jornada completa

Descripción de la vacante

XenonStack is seeking an experienced MLOps Engineer to deploy, monitor, and optimize agentic AI systems in production environments. You will work at the intersection of MLOps, DevOps, and Agentic AI to enable enterprises to confidently adopt AI agents at scale.

The role focuses on AI observability, reliability, and cross-functional collaboration with AI engineers, DevOps, and product managers, delivering measurable business outcomes through robust monitoring, cost-aware tuning, and compliance.

Formación

• 2–5 years of experience in DevOps, MLOps, or AI systems engineering.
• Hands-on with LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex).
• Familiarity with AgentOps tools (LangSmith, PromptLayer, Weights & Biases, Arize AI).
• Proficiency in Python and scripting for automation.
• Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes).
• Knowledge of monitoring & observability tools (Prometheus, Grafana, ELK, OpenTelemetry).
• Understanding of RAG pipelines, vector databases, and context orchestration.

Responsabilidades

• Deploy and maintain LLM-powered and multi-agent systems across cloud and on-prem environments.
• Integrate agents with enterprise APIs, knowledge bases, and third-party systems.
• Implement agentic observability frameworks to track performance, latency, cost, and accuracy.
• Monitor execution traces, context windows, and agent interactions for anomalies.
• Fine-tune agent configurations for cost efficiency, scalability, and response quality.
• Implement fallbacks, guardrails, and redundancy mechanisms to ensure reliability.
• Build automated pipelines to evaluate agent performance, safety, and compliance.
• Feed test results into continuous improvement loops with ML/AI engineers.
• Ensure agents follow enterprise security, governance, and compliance standards.
• Collaborate with Responsible AI teams to implement trust, safety, and audit mechanisms.
• Work with AI engineers, DevOps, and product managers to align operational reliability with business outcomes.
• Support customer deployments with customized monitoring and tuning.

Conocimientos

2–5 years DevOps/MLOps/AI systems

LLM orchestration frameworks

AgentOps tools

Python scripting

Cloud platforms & containers

Monitoring & observability tools

RAG pipelines & vectors

Herramientas

LangChain

LangGraph

LlamaIndex

LangSmith

PromptLayer

Weights & Biases

Arize AI

Descripción del empleo

About Xenonstack

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.

About Xenonstack

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

• Akira AI — Reasoning and agent orchestration. Turn models into collaborative, policy-governed agents that learn and act together.
• ElixirData — Agentic analytics intelligence. Explainable, decision-centric analytics for measurable business outcomes.
• NexaStack — Agentic infrastructure automation. Secure, compliant AI deployment across cloud, edge, and on-prem.
• MetaSecure — Trust, compliance and defense. Continuous assurance with AI-BOMs, risk scoring, and agentic security.

Our mission is to accelerate the world’s transition to AI + Human Intelligence by making agentic systems reliable, responsible, and enterprise-ready.

THE OPPORTUNITY

We are seeking an MLOps Engineer to deploy, monitor, and optimize agentic AI systems in production environments.

This role is at the core of AI observability and operational reliability, ensuring that multi-agent workflows perform consistently, safely, and efficiently. You’ll work at the intersection of MLOps, DevOps, and Agentic AI, enabling enterprises to confidently adopt AI agents at scale.

Key Responsibilities

• Agent Deployment & Operations
  • Deploy and maintain LLM-powered and multi-agent systems across cloud and on-prem environments.
  • Integrate agents with enterprise APIs, knowledge bases, and third-party systems.
• Monitoring & Observability
  • Implement agentic observability frameworks to track performance, latency, cost, and accuracy.
  • Monitor execution traces, context windows, and agent interactions for anomalies.
• Optimization & Reliability
  • Fine-tune agent configurations for cost efficiency, scalability, and response quality.
  • Implement fallbacks, guardrails, and redundancy mechanisms to ensure reliability.
• Evaluation & Feedback Loops
  • Build automated pipelines to evaluate agent performance, safety, and compliance.
  • Feed test results into continuous improvement loops with ML/AI engineers.
• Security & Compliance
  • Ensure agents follow enterprise security, governance, and compliance standards.
  • Collaborate with Responsible AI teams to implement trust, safety, and audit mechanisms.
• Cross-Functional Collaboration
  • Work with AI engineers, DevOps, and product managers to align operational reliability with business outcomes.
  • Support customer deployments with customized monitoring and tuning.

Skills & Qualifications

Must-Have

• 2–5 years of experience in DevOps, MLOps, or AI systems engineering.
• Hands-on with LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex).
• Familiarity with AgentOps tools (LangSmith, PromptLayer, Weights & Biases, Arize AI).
• Proficiency in Python and scripting for automation.
• Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes).
• Knowledge of monitoring & observability tools (Prometheus, Grafana, ELK, OpenTelemetry).
• Understanding of RAG pipelines, vector databases, and context orchestration.

Good-to-Have

• Exposure to multi-agent orchestration (MCP, A2A messaging, AgentBridge).
• Experience in Responsible AI / model evaluation frameworks.
• Familiarity with CI/CD pipelines for AI models and agents.
• Background in BFSI, GRC, SOC, or enterprise SaaS systems.

WHY SHOULD YOU JOIN US?

• Agentic AI Product Company

Work on next-gen AI platforms where agent reliability and observability define enterprise adoption.

• A Fast-Growing Category Leader

Join one of the fastest-growing AI Foundries, powering mission-critical AI agents for global enterprises.

• Career Mobility & Growth

Grow into roles such as AgentOps Lead, Reliability Engineer, or AI Systems Architect.

• Global Exposure

Manage enterprise-scale AgentOps deployments across regulated industries worldwide.

• Create Real Impact

Ensure that AI agents in production deliver measurable business outcomes.

• Culture of Excellence

Our values — Agency, Taste, Ownership, Mastery, Impatience, and Customer Obsession — empower you to build, innovate, and own outcomes.

• Responsible AI First

Contribute to trustworthy, explainable, and compliant AI agents that enterprises can rely on.

XENONSTACK CULTURE – JOIN US & MAKE AN IMPACT!

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 reliable and enterprise-ready.
• Obsessed with Simplicity – Turning complex agent operations into seamless, intuitive workflows.

Be a part of our mission to accelerate the world’s transition to AI + Human Intelligence — by ensuring AI agents are reliable, secure, and production-ready.