Krishna Kumar Singh

Krishna Kumar Singh

Solution Architect (Cloud) & DevOps Engineer

16+ years of experience in technology | Based in Greater Noida, India

About Me

I'm Krishna Singh, currently working as a Solution Architect (Cloud) and DevOps Engineer at Paytm in Noida. With over 16 years of experience in the tech industry, I specialize in designing scalable cloud solutions and implementing DevOps best practices. Based in Greater Noida, India, I am passionate about leveraging technology to solve complex business challenges.

Technical Skills

Cloud Platforms

  • Amazon Web Services
  • Google Cloud Platform
  • Microsoft Azure
  • Kubernetes
  • OpenStack

Model Serving & AI/LLM Tools

  • Triton Inference Server
  • vLLM
  • LiteLLM
  • TensorRT-LLM
  • DeepSeek R1
  • Meta LLaMA 2/3, Meta-70B

Containerization & Orchestration

  • Kubernetes (EKS, Colima, containerd)
  • Docker

CI/CD & DevOps Tools

  • GitHub Actions
  • Jenkins
  • Git

Infrastructure as Code

  • Terraform
  • Ansible
  • Packer

Monitoring & Observability

  • Prometheus
  • OpenResty VTS
  • Nagios
  • New Relic
  • Graylog2
  • Custom Dashboards

Programming Languages

  • Bash
  • Python

Work Experience

Sr. DevOps Manager

Paytm

Nov 2021 - Present | Noida, India
  • Designing scalable cloud solutions and implementing DevOps best practices
  • Managing infrastructure automation and CI/CD pipelines
  • Implementing monitoring and logging solutions

Technical Operations Architect

Info Edge India Ltd. (Naukri.com, 99acres, Jeevansathi, Shiksha)

Mar 2018 - Nov 2021 | Noida, India
  • Led technical operations for multiple platforms including Naukri.com, 99acres, Jeevansathi, and Shiksha
  • Architected and implemented scalable infrastructure solutions
  • Managed cloud infrastructure and DevOps practices

Sr. DevOps Engineer

Times Internet (Dineout)

Dec 2015 - Mar 2018 | Noida, India
  • Managed DevOps infrastructure for Dineout platform
  • Implemented CI/CD pipelines and automation solutions
  • Ensured high availability and performance of production systems

Member of Technical Staff (DevOps)

Elara Group (Housing, PropTiger & Makaan)

Dec 2013 - Oct 2015 | Noida, India
  • Led builds and release management team and AWS services management team with automation
  • Reduced AWS Infrastructure cost by 30% through automation initiatives
  • Ensured 24x7 availability of websites with zero downtime
  • Designed and implemented scalable web applications based on EC2 with fully automated deployment (high-availability, multi-scalable-tier VPC deployment)
  • Managed production web systems on AWS including ELB, app servers and database servers (MySQL, RDS)
  • Implemented comprehensive monitoring solutions (Nagios, New Relic, Graylog2, S3)
  • Automated product deployment in staging and production using Jenkins
  • End-to-end deployment ownership of production environment on AWS
  • Code management and quality monitoring with Git and Sonar
  • Technical expertise in Linux Server Configuration, Tomcat, Apache, Nginx, Solr, Bash Scripting, Networking
  • Managed both Production and staging servers across Local data center and AWS cloud

Technical Team Lead

Petronia Technologies

Oct 2009 - Dec 2013 | Noida, India
  • Led technical teams for multiple clients:
  • Ixigo.com / Indiahomes (Aug 2013 - Dec 2013): DevOps support and AWS infrastructure management
  • Guavus Network Systems (Feb 2013 - Aug 2013): Datacenter support and infrastructure management
  • Clickable Pvt. Ltd. / Syncapse (Dec 2011 - Feb 2013): DevOps and IT Infrastructure Planning on AWS
  • Vriti Infocom, Bagittoday (Sep 2010 - Nov 2011): System Administration and infrastructure management
  • Pine Labs India Pvt. Ltd. (Oct 2009 - Aug 2010): System Administration and technical support

Senior Linux System Administrator

Infinite Technologies NCR

Mar 2009 - Sep 2009 | New Delhi, India
  • Managed Linux server infrastructure
  • Implemented system security measures
  • Handled system administration tasks

Strengths

Learning Goals

AI & LLM Infrastructure

  • Deepen expertise in model deployment and inference optimization
  • Master high-throughput serving techniques (targeting 3500+ tokens/sec)
  • Explore advanced quantization and memory optimization strategies
  • Implement multi-model deployment in single processes using Triton backends

Model Serving & Deployment

  • Enhance proficiency with vLLM and sglang for efficient model serving
  • Implement TensorRT-LLM for optimized inference performance
  • Develop custom model deployment pipelines
  • Build and deploy specialized models for specific use cases

Cloud & Infrastructure

  • Advance knowledge in cloud-native AI infrastructure
  • Implement automated scaling solutions for LLM workloads
  • Optimize GPU resource utilization for AI workloads
  • Develop infrastructure as code templates for AI deployments

Career Development

  • Align career trajectory toward AI/LLM infrastructure specialization
  • Contribute to open-source AI infrastructure projects
  • Share knowledge through technical writing and presentations
  • Build expertise in emerging AI infrastructure technologies

Contact Me

Feel free to reach out to me for any opportunities or collaborations.

Email LinkedIn