Biswarup Ghosh
DevOps & MLOps Engineer | SRE · Cloud Engineer · Financial Domain | IMMEDIATELY AVAILABLE
Hire this person
Send a job offer directly to this candidate
About
DevOps, MLOps, and Cloud Engineer with 3 years of hands-on experience at Infosys Limited, building and operating cloud-native infrastructure for enterprise clients in the financial domain. Specialized in AWS infrastructure automation, Kubernetes orchestration, CI/CD pipeline design, SRE practices, real-time observability, and production ML deployment. Bridges infrastructure reliability with ML system operations — owning end-to-end pipelines, Kubernetes clusters, observability stacks, and production-grade RAG-based AI systems.
Immediately available for DevOps, MLOps, SRE, or Cloud Engineer roles in SaaS, FinTech, or AI-first companies.
Experience
Systems Engineer - Infosys Limited - Bhubaneswar, Odisha · Hybrid
(2022-01 - 2025-01)
- Designed and managed highly available AWS environments (EC2, ECS, ELB, VPC, IAM, Elastic Beanstalk) for enterprise financial workloads — ensuring fault tolerance, auto-scaling, and secure architecture
- Automated infrastructure provisioning with Terraform and Ansible — reducing manual deployment effort by 60% and eliminating configuration drift across dev, staging, and production
- Built GitHub Actions CI/CD pipelines automating build, test, containerization, and Kubernetes rollout — improving release frequency and reducing deployment failures
- Containerized applications with Docker and orchestrated multi-container workloads on Kubernetes with HPA — enabling zero-downtime deployments and self-healing clusters
- Configured Nginx as reverse proxy and load balancer — improving application response time by 25–30%
- Designed Prometheus + Grafana dashboards for Kubernetes clusters — tracking latency, error rates, CPU/memory utilization, and throughput in real time
- Implemented AWS CloudWatch centralized logging and automated alerting — enabling proactive anomaly detection and reducing MTTD for infrastructure incidents
- Led incident response, root cause analysis (RCA), and post-incident reviews for SLA-critical systems in the financial domain
- Hardened cloud security posture using IAM policies, security groups, network segmentation, and least-privilege access principles across AWS environments
- Deployed scalable ML inference services on Kubernetes with HPA auto-scaling — enabling high-availability model serving for production ML workloads
- Built end-to-end ML lifecycle CI/CD pipelines using GitHub Actions — automating model packaging, validation, container builds, and Kubernetes deployment
- Implemented ML observability with Prometheus + Grafana — monitoring inference latency, API error rates, and resource utilization across production ML endpoints
- Built a production RAG chatbot using Cohere LLM APIs + FAISS vector search — enabling context-aware document retrieval from internal knowledge bases
- Developed web applications using React.js, JavaScript, HTML/CSS — leveraging React Hooks for state management and Axios for RESTful API integration
- Provided L2/L3 support for Java-based banking applications — resolving complex production issues in Java, OOP, RESTful APIs, and Microservices architecture
- Designed and deployed a production-grade Retrieval-Augmented Generation (RAG) chatbot enabling context-aware responses from internal Infosys knowledge bases
- Integrated Cohere LLM APIs for NLU and built a FAISS vector search index for fast semantic similarity retrieval from internal document corpus
- Containerized with Docker, deployed on Kubernetes with HPA auto-scaling, CI/CD via GitHub Actions, and full observability via Prometheus + Grafana — monitoring API latency, error rates, and uptime
Education
Bachelor of Technology (B.Tech) - Asansol Engineering College, WB (2018 - 2021)
Diploma in Engineering - WBSCTVT&SD, West Bengal (2015 - 2018)