Senior DevOps Engineer

Overview

Sirion is the world’s leading AI–native Contract Lifecycle Management (CLM) platform, transforming how global enterprises manage their contracting journey. Powered by generative AI, Sirion delivers advanced extraction, conversational search, and AI-driven negotiation capabilities. With 7M+ contracts worth nearly $800B under management and consistent recognition from Gartner, IDC, and Spend Matters, Sirion continues to set the innovation benchmark for CLM.

For further details please visit www.sirion.ai

Power the Future of AI & Why This Role Matters

We are seeking an experienced and highly skilled Senior DevOps Engineer to strengthen our cloud, automation, and deployment ecosystem across our global SaaS platform.

This role is critical to ensuring reliability, scalability, performance, and security across our environments. You will shape CI/CD pipelines, infrastructure automation, monitoring frameworks, and large-scale deployments across cloud-native and containerized architectures.

The ideal candidate brings strong hands-on expertise in DevOps, cloud engineering, infrastructure automation—and experience supporting MLOps workflows, which are integral to our AI-led product ecosystem.

Shift Timings - Rotational ( Morning, General, Night)

How You’ll Make An Impact

• Build, automate, and optimize deployment pipelines and cloud infrastructure across AWS and Azure / GCP
• Lead scalable automation initiatives, including IaC, monitoring, observability, and performance engineering.
• Design and support containerized environments using Docker, Kubernetes or OpenShift.
• Enhance deployment architecture, reliability, and operational efficiency through best-in-class DevOps practices.
• Collaborate with Engineering, QA, and IT teams to ensure smooth deployments and timely issue resolution.
• Establish governance for deployment specifications, documentation, and environment configurations.
• Troubleshoot complex deployment issues and drive continuous improvement across systems and processes.
• Support backend systems, Java deployments, and integration with databases such as PostgreSQL, MongoDB, Redis, Elastic Search, Vector DB ( Qdrant )
• Implement and maintain MLOps workflows (model deployment, monitoring, versioning) in partnership with AI/ML teams.
• Manage Kubernetes-based ML deployments using Kubeflow, MLflow, Seldon, KServe, or Vertex AI.
• Optimize GPU/compute utilization, caching, batching, and inference efficiency.
• Implement model performance monitoring (latency, drift, hallucination, accuracy, cost metrics).
• Troubleshoot performance bottlenecks related to model serving, embeddings, vector databases, and orchestration tools
• Collaborate with InfoSec and backend teams to ensure secure model deployments, PII protection & compliance
• Implement end-to-end ML lifecycle using MLflow/Kubeflow/Vertex AI/SageMaker.
• Strengthen monitoring, alerting, and performance analytics using tools such as Prometheus, Nagios, Hyperic, etc.
  
  

Bachelor's degree in Computer Science or Engineering.

Experience & Technical Expertise

• 6+ years of DevOps experience in a cloud-native SaaS environment.
• Strong experience with AWS & Azure, cloud administration, and infrastructure management.
• Expertise in container orchestration: Docker, Kubernetes, OpenShift.
• Hands-on automation experience with Jenkins, Ansible, Puppet, Chef, Terraform.
• Good exposure to FinOps for cloud cost optimization.
• Experience with messaging systems: Kafka, Pulsar.
• Strong knowledge of version control tools: GitLab, GitHub, SVN, Bitbucket.
• Proficiency in monitoring tools such as Prometheus, Hyperic, Nagios, Cacti, Munin, Ganglia, etc.
• Linux administration expertise (Ubuntu, Red Hat, CentOS).
• Experience with Java deployments, Apache Tomcat, and HTTP Server.
• Strong scripting skills using Python, Shell, Groovy, PowerShell.
• MLOps experience—model deployment, model lifecycle management, pipeline automation, and monitoring using tools like MLflow, Kubeflow, SageMaker, or equivalent.
• Ability to work in rotational shifts (Morning, General, Night).
• Tools Understanding: Qdrant, LiteLLM, Langfuse, Torchserve or Trition Inference Server, AWS Bedrock and IBM WatsonX
  
  

We are an equal opportunity employer committed to diversity and inclusion. We do not discriminate based on race, color, gender, religion, national origin, disability, veteran status, or any other protected characteristic. We provide reasonable accommodations as required by law. These principles guide all aspects of employment including recruitment, development, promotions, compensation, and workplace programs.