Project Role : Operations Engineer

Project Role Description : Support the operations and/or manage delivery for production systems and services based on operational requirements and service agreement.

Must have skills : Agentic Orchestration, Agentic AI , AI Orchestration LLM

Good to have skills : NA
Minimum 7.5 year(s) of experience is required

Educational Qualification : 15 years full time education

Summary:
A Principal Engineer - Tools Platforms provides expert technical leadership across the infrastructure tooling ecosystem - spanning observability, automation, infrastructure-as-code, ITSM platforms, internal developer portals, and AI-augmented operations. The role is accountable for building, governing, and continuously improving the engineering platforms that enable Cloud, Network, Security, Database, and Voice towers to operate at scale with reliability. A key differentiator of this role is the ability to embed AI-augmented capabilities - LLM-driven runbook automation, agentic ITSM workflows, and intelligent alert correlation - directly into infrastructure platforms, accelerating toil reduction and operational intelligence across the organization.

Observability
- ELK/Splunk
- OpenTelemetry
- Jaeger/Zipkin
Automation IaC
- Terraform/Pulumi
- Ansible/Chef
- GitHub Actions/ArgoCD
- HashiCorp Vault
ITSM DevOps
- ServiceNow
- Jira/Confluence
- Xmaters

AI-Augmented Ops
- LLM runbook automation
- Agentic ITSM workflows
- AI alert correlation
- RAG knowledge bases
- LLMOps pipelines

Roles Responsibilities:
- Design, build, and operate enterprise observability platforms - Splunk - providing unified metrics, logging, and tracing across all infrastructure tiers with OpenTelemetry instrumentation standards
- Engineer and govern the IaC platform - Terraform or Pulumi - including module libraries, state management, policy-as-code (Sentinel/OPA), drift detection, and multi-cloud coverage across AWS and GCP
- Build and maintain CI/CD and GitOps pipeline infrastructure - GitHub Actions, ArgoCD - for infrastructure and application platform delivery operate the Internal Developer Portal (Backstage) for self-service provisioning
- Own ITSM platform engineering - ServiceNow workflow automation, CMDB reconciliation, PagerDuty/OpsGenie integrations,



and automated incident creation pipelines across all infrastructure towers
- Engineer LLM-powered runbook automation - integrating OpenAI, Anthropic Claude, or Google Gemini with infrastructure tooling to automate incident triage, resolution workflows, and knowledge base queries
- Build agentic ITSM workflows - multi-agent orchestration (LangChain, LlamaIndex, CrewAI) that autonomously handle incident classification, runbook execution, and stakeholder communication with human-in-the-loop controls
- Implement AI-powered alert correlation and noise reduction - LLM-based reasoning to group related alerts, suppress false positives, and surface actionable incident context to on-call engineers
- Design RAG architectures for infrastructure knowledge bases - enabling engineers to query runbooks, operational docs, and incident history through natural language interfaces backed by vector databases
- Engineer secret management infrastructure - HashiCorp Vault - dynamic secrets, PKI automation, and Kubernetes auth across multi-cloud and on-premises environments
- Mentor engineers across all towers set platform engineering standards, drive tooling roadmaps, and act as the highest technical escalation point for platform and AI tooling issues

Professional Technical Skills:
Mandatory Certifications

- Terraform Associate or Qualified- Splunk Professional -AWS DevOps Engineer Pro or GCP DevOps Engineer

- Certified Kubernetes Administrator (CKA)- HashiCorp Vault Associate

- Observability: Splunk - SLO engineering, OpenTelemetry, ELK/Splunk log pipelines, distributed tracing

- IaC Automation: Terraform (advanced) - modular design, policy-as-code, drift detection Ansible/Chef for configuration management

- CI/CD GitOps: GitHub Actions, ArgoCD - pipeline engineering, GitOps workflows, policy enforcement, infrastructure deployment automation

- ITSM Engineering: ServiceNow - workflow automation, CMDB integration, incident/problem/change API integration,



PagerDuty/OpsGenie connectivity

- Internal Dev Portal: service catalogue, golden path templates, self-service provisioning, and plugin development

- Secret Management: HashiCorp Vault - dynamic secrets, PKI automation, Kubernetes auth, multi-cloud secrets lifecycle

- LLM AI Tooling: OpenAI, Anthropic Claude, Google Gemini - prompt engineering, RAG architecture, vector databases (Pinecone, Weaviate, ChromaDB), LLMOps

- AI Orchestration: LangChain, LlamaIndex, CrewAI - agentic workflow design, multi-agent orchestration, tool calling, human-in-the-loop workflows

- Scripting Dev: Python (advanced) - platform tooling development, LLM SDK integration, infrastructure automation, API development

- FSI Compliance: PCI DSS, SOX, DORA - platform access controls, audit logging, policy-as-code enforcement, and regulatory evidence production
Preferred / Advantageous
- Crossplane for Kubernetes-native cloud resource provisioning
- eBPF-based observability - Cilium, Pixie, or Hubble - for deep infrastructure telemetry
- AI/ML infrastructure - GPU node management, model serving platforms (Triton, vLLM), or MLflow
- Platform engineering or SRE consulting background within financial services

Infrastructure Platform Engineering Tooling
- Observability, IaC, CI/CD, ITSM, and IDP platforms are reliable, well-governed, and actively adopted across all infrastructure towers - with measurable reductions in operational toil
- AI-augmented operations are deployed in production - runbook automation, agentic ITSM workflows, and LLM-powered alert correlation reduce MTTR and free engineers from repetitive work - IaC coverage is comprehensive and drift-free - environments reproducible, policy-compliant, and pipeline-deployable without manual intervention
- Engineering teams across all towers regard the Principal Engineer as the authoritative platform expert who removes blockers, sets the standard, and makes hard problems tractable

- 12-15+ years in platform, tools, or infrastructure engineering

- The candidate should have minimum 7.5 years of experience in Agentic Orchestration.

- This position is based at our Bengaluru office.

- A 15 years full time education is required.

Qualification 15 years full time education

📌 Operations Engineer (Bengaluru)
🏢 Accenture
📍 Bengaluru