Manish Ravikanti

About

Backend/infra-focused engineer who owned production systems for distributed ML experimentation (hyperparameter tuning across a cluster with GPU scaling, custom scheduling, and checkpoint-based fault tolerance). Also built and operated a low-latency log validation service using queued async workflows with idempotency, retries/backoff, and strong observability, plus experience building resilient Selenium-based browser automations for complex multi-step web flows.

Experience

Education

Key Strengths

• Built and owned an end-to-end distributed hyperparameter tuning platform with orchestration, scaling, and checkpointing
• Designed custom cluster scheduling to reduce resource imbalance and improve throughput
• Implemented fault-tolerant checkpoint/resume for long-running distributed training jobs
• Built low-latency backend processing using queues/workers to absorb traffic spikes
• Production reliability practices: retries with exponential backoff, idempotency/deduplication, stateless services, and job reprocessing on worker failure
• Strong observability implementation (structured logging, metrics, dashboards, alerting)
• API design for internal/external consumers with versioning, documentation, and token-based auth
• Browser automation robustness: stable selectors, explicit waits, Page Object Model, and handling flaky UI/network states