Headline

Build & Scale Infrastructure + Agentic AI | Building OpenSRE.in

About

SRE & AI Engineer. I work on reliable systems and put AI into production. Most of my career has been spent keeping services up: cloud infrastructure, automation, build pipelines, incident response. Over the last few years I've been pulling AI work into the same lane — applying SRE habits to LLM systems, evaluation, and the unglamorous parts of getting models into production. The two disciplines have more in common than the discourse suggests, and there's a useful niche for engineers who can speak both. What I bring: - Currently — Staff SRE at VMO India, building voice AI agent infrastructure and agentic AI systems in production. - OpenSRE — your AI SRE engineer. Open-source autonomous incident investigation: LangGraph multi-agent orchestration, Neo4j knowledge graph, 46 production skills. Live at opensre.in. Code: github.com/swapnildahiphale/OpenSRE. - Previously Staff SRE at Mobile Premier League — 100+ microservices on Kubernetes with Istio, HA AWS supporting 100M+ users on India's largest gaming platform, ELK at 10+ TB/day, observability on Prometheus/Thanos/Grafana, IaC with Terraform + Atlantis. - 10+ years across DevOps, SRE, and platform engineering — Linux, AWS, Kubernetes, Terraform, CI/CD, on-call. - Certifications: AWS Solutions Architect, RHCE/RHCSA, Red Hat Ansible Automation, Certified Jenkins Engineer. AI coursework (DeepLearning.AI): AI Agents in LangGraph, Long-Term Agentic Memory with LangGraph, Building Agentic RAG with LlamaIndex, Efficiently Serving LLMs, LangChain for LLM Application Development, ChatGPT Prompt Engineering for Developers. Connect if you work on production systems or AI in production. DMs open — happy to compare notes.

Location

Pune Division

AI stack

claude code

codex

cursor

langchain

langfuse

livekit

Work experience

Staff DevOps Engineer at Vimo, Oct 2023 - Present · 2 yrs 11 mos, On-site, Build the infra for AI Agents. Orchestrate the agents. Power real conversations. Keep voice Al alive in production. Helping a Health Platform modernize by applying DevOps and SRE practices.

Staff Site Reliability Engineer at Mobile Premier League (MPL), Jul 2022 - Oct 2023 · 1 yr 4 mos, Pune, Maharashtra, India, - Led the architecture and migration of 100+ of micro-services to a Kubernetes environment leveraging Istio Mesh - Engineered a highly available and scalable AWS infrastructure to accommodate the exponential growth and demanding workloads of MPL - Implemented a cutting-edge log management stack with ELK, effectively handling 10+ TB of daily log data across multiple geographical regions - Streamlined deployment strategy, selected optimal toolsets, and executed AMI-based deployments leveraging Harness and AWS EC2 Autoscaling Groups across multiple geographical regions - Designed and implemented Terraform and Atlantis-based IaC - Implemented Python and Serverless framework-based automations to address various infrastructure challenges - Extensive experience in observability, implementing robust monitoring using Prometheus, Thanos, Grafana, and Jaeger - Collaborated with data scientists and engineers to understand ML development workflows, Implemented POC on ML Observability - Held multiple roles including Staff SRE, Engineering Manager and DevOps Lead, showcasing versatility and leadership across roles.

Engineering Manager - DevOps & MLOps at Mobile Premier League (MPL), Jan 2022 - Jul 2022 · 7 mos, Pune, Maharashtra, India, - Bootstrapped MLOps team at MPL - Collaborated with data scientists and engineers to understand ML development workflows, Implemented POC on ML Model deployment and Observability - Certification on Machine Learning Model Deployment

DevOps Lead at Mobile Premier League (MPL), Feb 2019 - Jun 2022 · 3 yrs 5 mos, Pune Area, India

Senior DevOps Engineer at Crevise Technologies, Sep 2016 - Jan 2019 · 2 yrs 5 mos, Pune Area, India, "Helped an Airline company move to cloud!"-- Project lead, ansible development for an challenging, enterprise client (Cathay Pacific Airways), responsibilities include- directly interacting with client, managing team of ansible developers, biweekly travel to onsite (Hong Kong), designing and development of automation tasks with Ansible. Tasks automated with Ansible: Integration with Cisco ACI, Hitachi Data Systems and F5. Installation and configurations of application & database systems on RHEL vms. OS hardening, clustering, MSSQL cluster setups on Windows servers. Containerised an micro-services application with 10+ microservices. Setup entire test environment using docker and kubernetes. Integrated automated tests with CI pipeline with DroneCI. Implemented log monitoring with Graylog. As an AWS architect and DevOps design and develop an Highly Available, scalable infrastructure architecture with Autoscaling, terraform. Designed and Developed solution for incremental backups of MySQL, MariaDB and PostgeSQL. Setup ansible playbooks for Hashicorp Vault, Consul and Nomad. Experience with running GUI apps inside docker on AWS GPU instances.

DevOps Engineer at Crevise Technologies, Jun 2016 - Jan 2019 · 2 yrs 8 mos, Pune Area, India

DevOps Engineer at WhiteHedge Technologies, Sep 2015 - Jun 2016 · 10 mos, Pune Area, India, • Proposed a highly availabe and scalable architecture for a multi-tier application on AWS with CI/CD process & migrated it to AWS. • Setting up complete build and release pipeline for iOS and Android apps with Jenkins/TeamCity and Fastlane. Also for .NET based projects with TeamCity. • Developing Chef Cookbooks to Manage Infrastructure and automate processes. • Managing a production infrastructure on Amazon Web Services VPC utilizing AWS CodeDeploy, S3, EC2 Container Service, CloudFormation, docker including AutoScaling. • Managing build pipeline using Jenkins and various AWS services. • Writing shell and python scripts as per requirement. • Monitoring and loging application insides using DataDog and Loggly. • Setting up a build pipeline with Jenkins and AWS EC2 Container Service. • Troubleshooting the infrastructure and application issues as DevOps point of view. • Working with nodejs and actionhero framework.

DevOps Engineer at Webonise Lab, Nov 2014 - Aug 2015 · 10 mos, Pune Area, India, • Managing Linux kernel base server (VM & cloud servers) • Automated deployment of application using deployment tool(webistrano, capistrano, Cargo & chef) • Continuous integration with Jenkins. • Automate server configuration management & deployment process using Chef & Berkshelf. Using Ansible and basic knowledge of writing playbooks. • Write custom/own chef cookbook & use with the community cookbook. Basic knowledge in writing custom resources, test cookbooks using test kitchen. • Manage Production Server infrastructure environment, Collaborated with development team to troubleshot and resolve issues, Deliver product release with Frequent deployment with zero downtime deployment. • Deal with cloud services like AWS, Rackspace & different cloud server & load balancer management & Cloud server api tools. • Manage codebase versioning using Source control Management(Git, SVN) • Web hosting technology stack(ROR with passenger, Nginx+Unicorn, Django, Clojure, LAMP, LEMP, Tomcat & Glassfish server configuration & Reverse PassProxy). • Use of LDAP Centralized authentication with ssh key. • Automated backup for Database & cloud server snapshot and perform sanity check. • Securing OS with SSH key based, user limited authentication & securing all type of services using firewall, TCP wrapper, fail2ban & UFW. • Knowledge of OpenVZ virtualization (creating VM container, creating custom templates with pre- installed services), open stack & Vsphere(ESXi). • Mysql DB(creating user, managing privileges), Mongo DB with replica set configuration. • Server monitoring using nagios & install custom plugin & services to nagios client

Education

Bachelor of Engineering (B.E.), Computer Science, Savitribai Phule Pune University

Public links

github: https://github.com/swapnildahiphale

youtube.com: https://youtube.com/@bit-savvy