AI Platforms Engineer

PepsiCo Inc.; Hyderabad; On-site; INR 900,000 - 1,400,000; Full time

Job summary

PepsiCo Inc. in Hyderabad seeks an TheAI Observability Engineer to design and operationalize agentic AI solutions and establish an observability-driven operations center for scalable AI agent workloads.

The role emphasizes planning, tool execution, memory, and RAG workflows, with telemetry, incident triage, and production readiness. Collaboration with Data Science, IT, and product teams is essential to success.

Qualifications

• Bachelor’s degree in CS/AI/ML/Data Science or related field.
• 3–5+ years software engineering experience; 1+ years building observed AI/GenAI applications preferred.
• Experience with agentic frameworks and tool orchestration.

Responsibilities

• Build agent operations center capabilities for runtime management: agent registry, versioning, deployment tracking, and run histories.
• Enable incident triage, replay/debug runs, trace correlation, and root-cause analysis across agent steps.
• Implement operational dashboards and views for agent health: latency, success rate, cost per run, and loop detection.
• Instrument agent flows end-to-end using OpenTelemetry (or equivalent) with telemetry pipelines.
• Collaborate with SRE/observability teams to ensure production-grade monitoring and alerting.
• Build CI/CD pipelines for agent services and onboarding templates.

Skills

Python

CI/CD

Observability

Distributed tracing

OpenTelemetry

GenAI

Problem solving

Collaboration

Education

Bachelor’s in Computer Science or related field

Tools

LangChain

Semantic Kernel

AutoGen

Crew.ai

Azure

AWS

GCP

Kubernetes

AKS

EKS

Vector databases

Job description

Overview

TheAI Observability Engineer (Agentic Frameworks & AI Agent Operations Center Developer)builds and operationalizesagentic AI solutionsusing modern orchestration frameworks and contributes to anAI Agent Operations Centerthat enables safe, reliable, and observable agent behavior at scale. This role focuses on developing agent workflows (planning, tool execution, memory, and RAG), integrating guardrails and evaluations, and delivering operational capabilities such as run management, telemetry, and incident triage for production agents.

Responsibilities

• AI Agent Operations Center (70%)
  • Build “operations center” capabilities for agent runtime management: agent registry, versioning, deployment tracking, and run histories
  • Enable operational workflows such as incident triage, replay/debug runs, trace correlation, and root-cause analysis across agent steps
  • Implement operational dashboards and views for agent health: success rate, latency, tool failure rate, cost per run, and loop detection
  • Instrument agent flows end-to-end usingOpenTelemetry(or equivalent), enabling correlation across prompts, tool calls, retrieval, and responses
  • Implement semantic conventions and tagging standards (agent name/version, tool name, model provider, environment, tenant/app)
  • Partner with SRE/observability teams to ensure production-grade monitoring, alerting, and operational readiness
• Collaboration with Teams (10%)
  • Collaborate with transformation teams and business stakeholders to understand requirements and tailor AI agents to specific domains.
  • Work closely with AI platform teams to build scalable and cross-domain AI agents while ensuring end-to-end observability.
• Integration & Deployment (10%)
  • Build and maintain CI/CD pipelines for agent services and operations center components, including automated testing and deployment
  • Automate onboarding for new agent use cases (templates, scaffolding, configuration checks)
  • Drive best practices for secure, scalable, and cost-effective agent deployments
• Continuous Learning (10%)
  • Stay updated with the latest advancements in AI and machine learning technologies and integrate these into existing or new AI agents.
  • Conduct thorough testing and validation to ensure the reliability and accuracy of AI agents and solutions.

• Decision-Making Autonomy Moderate – Significant autonomy in the technical aspects of AI model development and implementation, working under the strategic direction provided by the Senior AI Solutions leads.
• Supervision Required Moderate – Operates with general guidance from the Senior AI Solutions leads, with regular updates for alignment and support.
• Complexity of Role High – The role requires managing complex AI/ML projects, working with large datasets, and ensuring successful integration with existing systems while maintaining scalability.
• Cross-Functional Interactions Yes – Regular interaction with Data Science, Engineering, IT, digital products and business stakeholders to ensure effective AI solution Observability.

Qualifications

Key Skills/Experience Required Minimum Qualifications:

• Education: Bachelor’s in Computer Science, AI/ML, Data Science, or a related field.
• Experience: 3–5+ years of software engineering experience; 1+ years building and observe AI/ML or GenAI applications preferred
• Required Expertise:

• • Hands-on experience withagentic frameworks(Crew.ai, LangChain, Semantic Kernel, AutoGen, or similar)
  • Proficiency inPython(primary) and familiarity with APIs/microservices patterns
  • Strong experience withRAGpatterns (embeddings, vector search, retrieval evaluation, chunking strategies)
  • Experience with cloud environments (Azure/AWS/GCP) and containerized deployments (Kubernetes/AKS/EKS)
  • Familiarity with observability fundamentals (logs/metrics/traces) and production troubleshooting
  • Experience building internal developer platforms or operational consoles (agent registry, run tracking, dashboards)
  • Familiarity with OpenTelemetry, distributed tracing, and telemetry pipelines
  • Experience with Azure AI Search / vector databases, prompt/version management, and evaluation frameworks
  • Knowledge of Responsible AI practices: data handling, safety guardrails, audit trails, and redaction strategies

FinOps exposure: token/GPU cost optimization and chargeback/showback reporting

Drentiating Competencies Required

• Technical Proficiency: Agent orchestration design (planning, tool execution, memory, RAG), Strong engineering discipline: testing, versioning, CI/CD, automation, Operational mindset: reliability, debuggability, and incident response support
• Problem-Solving: Ability to translate business challenges into technical solutions.
• Collaboration Skills: Effective at working within cross-functional teams.
• Agility: Flexibility to adapt to changing requirements and new technologies.
• Communication Skills: Capable of explaining complex technical concepts to non-technical stakeholders.