Nikhil Sai Patnam

Product Manager

Chittoor, Andhra Pradesh, India1 yr experience

AI EnabledAI ML Practitioner

Key Highlights

Expert in AI-driven quality assurance and backend development.
Reduced manual testing cycles by 50% through automation.
Engineered evaluation frameworks for production-grade AI validation.

Stackforce AI infers this person is a Backend-heavy Fullstack Engineer specializing in AI Quality Assurance and Test Automation.

Contact

Skills

Core Skills

Test AutomationAi Quality AssuranceBackend DevelopmentQuality Assurance

Other Skills

PlaywrightPytestAI Voice AgentRAGDjangoGoSpring BootDatadogTemporalCypressTestRailAWSRHELSoftware Development Life Cycle (SDLC)Artificial Intelligence (AI)

About

SDET with deep expertise in AI/LLM quality assurance and backend development. SDET & AI/LLM Quality: I specialize in testing intelligent systems. Strong expertise in test automation frameworks (Cypress, Playwright, Pytest) combined with deep understanding of system architecture and AI evaluation methodologies. At Apna, I evaluated AI Voice Agent features across different models, engineered evaluation frameworks, and built systematic approaches to AI quality assurance moving beyond manual testing to production-grade AI validation. Backend Development: I've also contributed to backend development across Django, Go (Gin), and Spring Boot. Worked on designing and developing features, solving critical issues, and building observability into systems. This backend knowledge ensures I test systems with architectural understanding, not just surface-level validation. My Unique Combination: SDET + AI Systems + Backend Engineering. I combine test automation expertise with deep AI system understanding and backend development knowledge. This allows me to: 1. Design systematic test strategies for AI-driven backend services 2. Understand the systems calling AI models (not just test the AI) 3. Build reliable, observable systems that users trust What I Believe: Quality is built in, not bolted on. Especially for AI systems test early, evaluate systematically, monitor continuously. Tech Stack: Cypress, Playwright, Pytest | Python, Go, Django, Spring Boot | AI evaluation, RAG frameworks, LLM understanding | Datadog, observability Always interested in: AI-driven features, quality automation, system design, observability.

Experience

1 yr

Total Experience

11 mos

Average Tenure

1 mo

Current Experience

Swiggy

SDET

May 2026 – Present · 1 mo · Bengaluru, Karnataka, India · On-site

Apna

SDET 1

Jun 2025 – May 2026 · 11 mos · Bengaluru, Karnataka, India · On-site

1. Test Automation & Coverage: Contributed to and expanded Playwright + Pytest automation suite for UI and API testing, increasing test coverage and reducing manual testing cycles by 50%.
2. AI-Powered Quality Assurance: Owned end-to-end testing of AI Voice Agent; verified performance across different LLM models; engineered system prompts and response schema for desired LLM output; designed RAG-based evaluation framework with LLM-as-judge for non-deterministic responses enabling production-grade AI feature validation.
3. Cross-Functional Collaboration & Risk Mitigation: Partnered across Product, Design, and Development teams from PRD grooming through deployment; highlighted technical risks and edge cases early accelerating feature alignment and reducing mid-stage pivots.
4. End-to-End Feature Ownership: Took complete ownership of features across development and testing from design and implementation (HLD/LLD), test execution; identified and implemented optimizations, resolved critical bugs, and ensured reliable rollouts with zero critical production issues.
5. Backend Development & System Integration: Developed backend features across Django, Go (Gin), and Java (Spring Boot) frameworks; owned end-to-end solutioning (problem analysis, HLD/LLD design, implementation, and verification); integrated 40+ communication channels (WhatsApp, SMS, Email) into existing features, increasing customer engagement and feature adoption; Worked on Temporal-based workflow orchestration, resolving critical stability issues: reduced workflow failures by 40%, optimized call dropout rates, eliminated candidate flow bottlenecks; integrated Temporal with Datadog for production observability.
6. Observability, Debugging & Production Monitoring: Configured Datadog alerts, GCP Cloud Scheduler, and anomaly detection for owned features; debugged production issues using GCP Log Explorer and trace analysis; reduced mean-time-to-resolution by 35%; served as on-call engineer for owned features.

PlaywrightPytestAI Voice AgentRAGDjangoGo+4

Securonix

Software Engineer Intern

Jul 2024 – May 2025 · 10 mos · Bengaluru, Karnataka, India · On-site

1. Test Automation & Coverage: Designed and executed 200+ Cypress automation test cases using Page Object Model, achieving 90% end-to-end UI test coverage and reducing manual testing effort by 40% for critical workflows.
2. Manual Testing & Quality Assurance: Managed 300+ functional, regression, and integration test cases in TestRail; authored comprehensive test documentation (test plans, cases, bug reports) following ISTQB best practices, ensuring robust validation of features pre-release.
3. Infrastructure Management & DevOps: Administered RHEL servers across 5 AWS test environments; performed build deployments from dev to production-like servers, including version-specific application upgrades/downgrades (Tomcat, Redis), build compatibility verification, and hotfix validation. Optimized infrastructure costs by monitoring and scheduling service start/stop cycles, reducing cloud spend by ~15% through resource utilization improvements.
4. Cross-functional Collaboration & Customer Interaction: Partnered with developers and product managers to resolve critical vulnerabilities; conducted customer verification calls to validate reported issues and confirm fixes reducing bug resolution time by 25%.

CypressTestRailAWSRHELTest AutomationQuality Assurance