download PDF

Education

San Jose State UniversityAug 2024 — May 2026
MS Software Engineering · CGPA: 3.57/4.0Coursework: Enterprise Distributed Systems, Machine Learning, NLPResearch Assistant, Agentic AI Systems (Sep 2025 — May 2026) · Teaching Assistant, Deep Learning (CMPE 258) and Data Mining (CMPE 255) (Aug 2025 — Apr 2026)
GITAM UniversityJun 2014 — Apr 2018
B.Tech Computer Science and Engineering

Experience

Accenture— Dell SupportAssistclient: Dell Technologies
Aug 2021 — Jul 2024
Senior Software Engineer
  • ▸Built C#/.NET microservices for Dell SupportAssist — diagnostics, driver/BIOS update delivery with signature verification, and telemetry for services processing 2M+ active devices
  • ▸Re-architected scan status for 15–20-minute diagnostic workflows from client polling to WebSocket push, cutting steady-state status-request load ~60%
  • ▸Built the in-app AI Virtual Assistant experience with device-context injection and assistant-triggered actions
  • ▸Architected Single-SPA micro-frontend integration (Angular 13 + React), cutting release coordination from 2 weeks to 3 days
  • ▸Mentored junior engineers and onboarded new hires; led code reviews and drove testing and safe-deployment practices
C# / .NETWebSocketsAngularReact
TCS
Jun 2018 — Aug 2021
Software Engineer
  • ▸Developed Java Spring Boot microservices for TCS Optumera’s space optimization module, processing 1,000+ retail parameters to generate recommendations for 1,400+ stores
  • ▸Engineered distributed search and optimization APIs with Redis caching, sustaining sub-200ms P95 across 2M+ SKU records
  • ▸Implemented multi-tenant SSO with Spring Security OAuth2, JWT, and tenant-scoped claims across 3+ applications
  • ▸Virtualized dashboard rendering for 100K+ SKU tables, cutting render time from ~800ms to ~120ms
JavaSpring BootRedisOAuth2Angular

Projects

Archon

Autonomous agent in Python — planner/executor/reflector with a typed middleware chain (schema validation, retries, tracing on every tool call) and a statistical evaluation harness: seeded runs, per-step traces, and a failure-mode taxonomy.

PythonAgentsEval
Sentinel

GitHub App that reviews PRs via BM25 + dense (pgvector) retrieval, cost guardrails, and a 98-fixture eval harness — per-category P/R/F1, regression-gated in CI.

FastAPIpgvectorBM25
Kairos

Multi-tenant OKR tracker that enforces tenant isolation in PostgreSQL with Row-Level Security, not in application code.

Spring Boot 3.3PostgreSQL 16Redis 7
Helios

WAL + LSM storage, Gorilla compression, label-postings filtering, a PromQL subset, streaming EWMA anomaly detection, and optional 3-node Raft replication.

GoLSM-treeGorilla
NeuroLens

MVP adversarial-ML research: from-scratch PyTorch models (no torchvision pretrained), FGSM and PGD attacks implemented from the original papers, defenses, and a multimodal-to-unimodal attack-transfer experiment.

PyTorchCLIP-lite

Skills

AI / AgentsAgent orchestration & tool calling, LLM evaluation (golden sets, regression gating), RAG (hybrid retrieval), PyTorch, W&B
LanguagesPython, TypeScript, C#, Java, Go, SQL
BackendFastAPI, C# / .NET, Spring Boot, gRPC, WebSockets
FrontendReact, Next.js, Angular, Tailwind CSS
Data / InfraPostgreSQL, pgvector, Redis, Docker, GitHub Actions
ConceptsDistributed systems, Postgres Row Level Security, LSM-tree, Raft consensus