DevOps Engineer

KnowledgeWorks Global Ltd.; Mumbai; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

KnowledgeWorks Global Ltd. in Mumbai is seeking an experienced Observability and DevOps leader to design and implement an end-to-end observability and alert stack for web and AI/ML services, covering Prometheus, Grafana, ELK/OpenSearch, and Datadog.

You will own scaling infrastructure across on-prem and cloud, apply IaC with Terraform and Ansible, lead CI/CD with Jenkins, GitHub Actions or ArgoCD, containerize with Docker and Kubernetes, and embed security checks into pipelines.

Qualifications

• 5-10 years of hands-on DevOps/SRE/Infrastructure engineering experience, with 2-3 years in senior/lead capacity.
• Strong Git-based workflows and repository management at scale (GitHub/GitLab/Bitbucket).
• Cloud platforms exposure (AWS, Azure, and/or GCP) with on-premise/hybrid infra experience.
• Expert-level Infrastructure as Code (Terraform, Ansible, CloudFormation, or Pulumi).
• Kubernetes and Docker experience, including multi-cluster management and CI/CD end-to-end.

Responsibilities

• Design and implement end-to-end observability & alert stack for web apps and AI/ML services.
• Develop tooling like Prometheus, Grafana, ELK/OpenSearch, Datadog; enable AI observability signals.
• Lead infrastructure scaling across on-prem and cloud with capacity planning and cost optimization.
• Embed security checks (SAST/DAST, secrets scanning) into CI/CD pipelines (DevSecOps).
• Provision and manage GPU infra for model deployment; optimize multi-tenant GPU usage.
• Drive CI/CD pipelines (Jenkins, GitHub Actions, ArgoCD/Flux) and containerization ( Docker/Kubernetes ).
• Collaborate with architects and data scientists to translate designs into infra and delivery plans.

Skills

DevOps/SRE leadership

Cross-functional collaboration

SRE best practices

Security and compliance awareness

Networking fundamentals

Automation scripting

Cloud architecture

Tools

Prometheus

Grafana

ELK/OpenSearch

Datadog

Terraform

Ansible

Jenkins

GitHub Actions

ArgoCD

Flux

Docker

Kubernetes

Helm

SAST/DAST tools

SonarQube

Snyk

Checkmarx

OWASP DependencyCheck

Trivy

Grype

Clair

Cosign/Sigstore

HashiCorp Vault

AWS Secrets Manager

Azure Key Vault

NVIDIA CUDA

Python

Bash

Go

Job description

Observability Strategy (Web & AI Applications)

• Design and implement an end-to-end observability & alert stack covering both traditional web applications and AI/ML services.
• Develop and maintain tooling such as Prometheus, Grafana, ELK/OpenSearch, Datadog, or equivalent
• Build AI-specific observability: model latency/throughput tracking, GPU utilization, token usage, drift detection, and inference quality signals.

Infrastructure Scaling & Reliability:

• Design and manage infrastructure capable of scaling across on-premise data centers and public cloud
• Own capacity planning, load testing, auto-scaling, and cost-optimization initiatives across compute, storage, and networking.
• Implement Infrastructure as Code (Terraform, Ansible, or equivalent) to ensure environments are reproducible, version-controlled, and auditable.
• Lead disaster recovery, backup, and high-availability strategy for critical systems.

DevOps & CI/CD Delivery :

• Partner closely with Solution Architects to translate project and system designs into concrete DevOps execution plans.
• Design, build, and maintain CI/CD pipelines (Jenkins, GitHub Actions or ArgoCD/Flux for GitOps) across multiple projects and teams.
• Containerize and orchestrate applications using Docker and Kubernetes, including Helm chart and manifest management.
• Embed security and compliance checks (SAST/DAST, secrets scanning, image scanning) directly into the delivery pipeline (DevSecOps).
• Provision, configure, and manage GPU infrastructure (on-prem clusters and cloud GPU instances) for model
• Deploy, scale, and monitor ML/LLM models in production using tools such as Triton Inference Server, vLLM,
• Optimize GPU utilization, cost, and throughput across multi-tenant workloads; manage CUDA/driver/toolkit
• Collaborate with data science/ML engineering teams on MLOps pipelines - model versioning, experiment
• 5-10 years of hands-on DevOps/SRE/Infrastructure engineering experience, including at least 2-3 years in a senior or lead capacity.
• Deep expertise in Git-based workflows and repository management at scale (GitHub/GitLab/Bitbucket).
• Strong background in cloud platforms (AWS, Azure, and/or GCP) and on-premise/hybrid infrastructure.
• Expert-level skills with Infrastructure as Code (Terraform, Ansible, CloudFormation, or Pulumi).
• Strong Kubernetes and Docker experience, including multi-cluster and multi-environment management.
• Hands-on experience building and maintaining CI/CD pipelines end to end.
• Working knowledge of GPU infrastructure (NVIDIA CUDA, drivers, NCCL) and experience deploying ML/AI models to production.
• Proficiency in scripting/automation languages: Python, Bash, and/or Go.
• Solid understanding of networking, load balancing, DNS, and security fundamentals in distributed systems.
• Experience partnering with architects and engineering leads to translate designs into infrastructure and delivery plans.
• Hands-on with SAST, DAST, and SCA tooling (e.g., SonarQube, Snyk, Checkmarx, OWASP DependencyCheck) integrated directly into CI/CD pipelines.
• Container and image security: vulnerability scanning (Trivy, Grype, Clair), minimal/hardened base images, and signed/verified image provenance (Cosign/Sigstore).
• Familiarity with Secrets management and credential hygiene using tools such such as HashiCorp Vault, AWS Secrets Manager, or Azure Key Vault
• Excellent communication skills and comfort operating cross-functionally with development, data science, and product teams.