Agentic Infrastructure Observability Engineer

XenonStack; Mohali; On-site; INR 1,400,000 - 2,200,000; Full time

Job summary

XenonStack is seeking an Agentic Infrastructure Observability Engineer to design and implement end-to-end observability for AI-native and multi-agent systems. You will monitor agents, pipelines, and infrastructure to ensure reliability, transparency, and cost efficiency.

You will work with AgentOps, DevOps, and Data teams to embed observability into CI/CD and build plugins for LLMs, agents, and data pipelines, shaping enterprise AI reliability at scale.

Qualifications

• 3–6 years of experience in SRE, DevOps, or Observability Engineering.
• Strong knowledge of observability tools (Prometheus, Grafana, ELK, OpenTelemetry, Jaeger).
• Experience with cloud-native infrastructure (AWS, GCP, Azure) and Kubernetes monitoring.
• Proficiency in Python, Go, or Bash for scripting and automation.
• Understanding of AI/LLM pipelines, RAG systems, and vector databases.
• Hands-on with CI/CD pipelines and monitoring-as-code.

Responsibilities

• Design and implement observability pipelines covering metrics, logs, traces and cost telemetry.
• Track LLM usage, context windows, token allocation, and multi-agent interactions.
• Define and monitor SLOs, SLIs, and SLAs for agentic workflows and inference infrastructure.
• Develop automation and tooling, integrate observability into CI/CD and AgentOps pipelines.
• Provide executive-level reporting on reliability and adoption metrics.

Skills

SRE/DevOps

Observability engineering

Python/Go/Bash

AI/LLM pipelines

CI/CD pipelines

Tools

Prometheus

Grafana

ELK

OpenTelemetry

Jaeger

Kubernetes monitoring

AWS

GCP

Azure

Job description

Agentic Infrastructure Observability Engineer

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

Inference AI Infrastructure for Agentic Systems→nexastack.ai

Our mission is to accelerate the world’s transition toAI + Human Intelligenceby building platforms that arescalable, reliable, and observable by design.

THE OPPORTUNITY

We are seeking anAgentic Infrastructure Observability Engineerto design and implementend-to-end observability frameworksfor AI-native and multi-agent systems.

This role sits at the heart ofAgentOps and Reliability Engineering— ensuring thatagents, pipelines, and infrastructureare monitored, measurable, and continuously optimized.

If you thrive onmetrics, monitoring, and making complex systems transparent and reliable, this role offers a chance to define observability for the next generation of enterprise AI.

KEY RESPONSIBILITIES

Observability Frameworks

Design and implementobservability pipelinescovering metrics, logs, traces, and cost telemetry for agentic systems.

Agentic AI Monitoring

TrackLLM usage, context windows, token allocation, and multi-agent interactions.

Build monitoring hooks intoLangChain, LangGraph, MCP, and RAG pipelines.

Reliability & Performance

Define and monitorSLOs, SLIs, and SLAsfor agentic workflows and inference infrastructure.

Conduct root cause analysis ofagent failures, latency issues, and cost spikes.

Automation & Tooling

Integrate observability intoCI/CD and AgentOps pipelines.

Develop custom plugins/scripts to extend observability for LLMs, agents, and data pipelines.

Work withAgentOps, DevOps, and Data Engineering teamsto ensure system-wide observability.

Provideexecutive-level reportingon reliability, efficiency, and adoption metrics.

Implementfeedback loopsto improve agent performance and reduce downtime.

Stay updated withstate-of-the-art observability and AI monitoring frameworks.

SKILLS & QUALIFICATIONS

Must-Have

• 3–6 years of experience inSRE, DevOps, or Observability Engineering.
• Strong knowledge ofobservability tools(Prometheus, Grafana, ELK, OpenTelemetry, Jaeger).
• Experience withcloud-native infrastructure (AWS, GCP, Azure)and Kubernetes monitoring.
• Proficiency inPython, Go, or Bashfor scripting and automation.
• Understanding ofAI/LLM pipelines, RAG systems, and vector databases.
• Hands-on withCI/CD pipelines and monitoring-as-code.

Good-to-Have

• Experience withAgentOps tools(LangSmith, PromptLayer, Arize AI, Weights & Biases).
• Exposure toAI-specific observability(token usage, model latency, hallucination tracking).
• Knowledge ofResponsible AI monitoring frameworks.
• Background inBFSI, GRC, SOC, or other regulated industries.

WHY SHOULD YOU JOIN US?

Agentic AI Product Company

Build observability frameworks fornext-gen enterprise AI systems.

A Fast-Growing Category Leader

Be part of one of the fastest-growingAI Foundries, powering mission-critical agent deployments.

Career Mobility & Growth

Advance into roles likeReliability Architect, AgentOps Lead, or Head of Observability.

Global Exposure

Work on observability challenges acrossFortune 500 enterprises and global innovators.

Create Real Impact

Ensuretransparency, trust, and resiliencein production-grade AI systems.

Culture of Excellence

Our values —Agency, Taste, Ownership, Mastery, Impatience, and Customer Obsession— give you autonomy to innovate and accountability to deliver.

Responsible AI First

Help enterprises adopt AI that isnot just powerful, but explainable and auditable.

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 observability and trust an integral part of enterprise AI.

Obsessed with Simplicity – Turning complex monitoring into seamless, actionable insights.

Be part of our mission toaccelerate the world’s transition to AI + Human Intelligence— by making agentic AI systemstransparent, observable, and reliable at scale.