Ankush Prajapati
Open to work1 years experienceDevOps Engineer
DevOps & AI Infrastructure Engineer
Standing Rank
Rank Not Available
Developer Badges
No badges earned yet
Skills & Technologies
37 skillsWork Experience
Solution Engineer
Quality Kiosk Technologies Pvt. Ltd.
- Architected and built a Self-Service Banking Tester Portal (FastAPI + MySQL backend), used by 15+ QA engineers across core banking domains, cutting synthetic test data turnaround from days to under 10 minutes.
- Containerized the application with Docker and deployed it on AWS EC2, with a GitHub Actions CI/CD pipeline automating the build-test-deploy workflow.
- Integrated GenRocket GMUS via REST API for automated data generation, configured through an interactive Tester Studio UI.
- Engineered a topological sort-based dependency resolver enforcing referential integrity across multi-table parent-child relationships, eliminating FK constraint violations.
- Deployed LangGraph-based AI agents integrated with the portal backend to auto-map natural language requests to data generation configs, reducing manual studio configuration effort.
- Implemented RBAC access control and multi-format export pipelines (CSV, Excel, JSON, XML, SQL, PDF).
- Architected and deployed a privacy-first, Multi-Agent RAG system using LangGraph to process complex, multi-domain enterprise queries (HR, IT, Security) with 100% local execution via Ollama, ensuring zero enterprise data leakage.
- Developed a dynamic multi-agent orchestration graph featuring a Query Rewriter for conversational memory, a Guardrails node for out-of-scope filtering, and an Intent Router that triggered parallel domain-specific agents for multi-topic queries.
- Engineered a hybrid retrieval pipeline combining Dense Vector Search (ChromaDB) and BM25 keyword retrieval, optimized with a Cross-Encoder reranker to improve retrieval precision and minimize context dilution.
- Built an automated LLM-as-a-Judge evaluation suite using DeepEval across 50+ enterprise test cases, measuring faithfulness, answer relevancy, and contextual precision while reducing hallucinations to near-zero.
- Integrated Arize Phoenix observability with OpenTelemetry traces to monitor end-to-end agent execution, retrieval quality, latency, and root-cause analysis across the complete workflow.
- Worked on core banking domain projects spanning data validation, schema testing, and data quality assurance across multiple banking product lines, validating and remediating 9–10 million records across production banking schemas.
- Authored complex SQL queries in Sybase to perform field-level validations, cross-table reconciliations, duplicate detection, null checks, and constraint verification across large-scale transactional datasets.
- Managed and executed test cases and defect tracking in Azure DevOps; authored structured test plans, linked test evidence to work items, and coordinated defect lifecycle from discovery to closure.
- Executed and monitored SAP BODS pipeline jobs for ETL processing; validated source-to-target data transformations and ensured pipeline output met schema compliance standards.
- Delivered 2 end-to-end POC engagements for test data management and synthetic data generation, reducing manual test data setup effort and demonstrating production feasibility to client stakeholders.
- Leveraged GenRocket GMUS to configure and execute data generation workflows; engineered REST API request bodies to push generated datasets directly into client databases.
- Tested and validated client-facing APIs using Postman — crafting request collections, verifying response schemas, and confirming data integrity.
Projects
Self-Healing Kubernetes Infrastructure with Automated Incident Response
- Provisioned a Kubernetes cluster and supporting cloud infrastructure using Terraform, replacing manual setup with version-controlled infrastructure-as-code.
- Deployed a containerized application to the cluster via Kubernetes manifests/Helm charts, with a GitHub Actions CI/CD pipeline automating test, build, image push, and deployment on every merge.
- Built a Prometheus, Grafana, and Alertmanager observability stack to detect failure patterns in real time (crash loops, error-rate spikes, resource exhaustion), with a live dashboard tracking request latency and error rate.
- Built an automated remediation service that receives Alertmanager webhooks and takes corrective action — restarting crash-looping deployments or rolling back to the last known-good Helm release — reducing incident response time from a manual process to an automatic one, with status reported to Slack.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Achievements Not Earned
Special rewards, developer badges, system recognition certificates, and conceptual milestones will display here.
About Details
Professional Bio
Engineer with 1 year of experience across the DevOps lifecycle (containerization, CI/CD, cloud, Kubernetes) and applied AI engineering (LangGraph, RAG, LLM evaluation). Built and deployed production systems end-to-end, from infrastructure provisioning to monitoring.
PG Diploma in Big Data Analytics
Centre for Development of Advanced Computing (CDAC) (2025 - 2025)
Bachelor of Engineering in Information Technology
Thakur College of Engineering and Technology (2021 - 2024)