Vyshnavi DP — Software & AI Engineer

I build AI agent workflows
and the evals that prove they work.

Senior software engineer with 6+ years shipping production systems — C#/.NET at Accenture on Dell SupportAssist and Java at TCS. Now building agent workflows and the evals that measure them.

View workEmail meResume
core
Python · TypeScript · Java · C#/.NET · Go
focus
LLM evals · RAG · agent orchestration · full-stack systems

Open to SWE & AI engineering roles · on OPT · San Jose, CA

6 years

industry experience

Accenture (Dell) · TCS

2M+

active devices

services I owned · SupportAssist

1,400+

stores optimized

TCS · space optimization

98

eval fixtures

Sentinel · CI regression gate

Selected work

All projects

agent systems

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.

180+
Test suite
5
Eval metrics
Bootstrap CI
Significance
Python · Agents · EvalCase study Code

applied ai

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.

98
Eval fixtures
4
Categories scored
−5% F1
CI gate
Python · FastAPI · Next.js · PostgreSQLCase study Code

more systems

KairosMulti-tenant OKR tracker that enforces tenant isolation in PostgreSQL with Row-Level Security, not in application code.Spring Boot 3.3 · PostgreSQL 16 — working studyHeliosTime-series database in Go — built from first principles.Go · LSM-tree — single-node stableNeuroLensMVP adversarial-ML research: a cross-modal CLIP → ResNet transfer study.PyTorch · CLIP-liteAdaptiveRateGuardDistributed rate limiter in Go with a gradient-boosting predictor sidecar.Go · Redis · gRPC
Everything on GitHub

Experience

Aug 2021 — Jul 2024

Senior Software Engineer · Accenture

Client: Dell Technologies · SupportAssist

  • C#/.NET microservices for Dell's preinstalled PC health platform: hardware diagnostics and scan orchestration.
  • Catalog-driven BIOS, driver, and firmware update delivery with signature and hash verification.
  • Telemetry-driven predictive failure detection for batteries and storage drives.
  • In-app AI Virtual Assistant with device-context injection and assistant-triggered actions.
  • Re-architected long-running scan status from client polling to WebSocket push with resumable progress state, cutting steady-state status-request load ~60%.
  • Mentored junior engineers, onboarded new hires, and led code reviews.

Jun 2018 — Aug 2021

Software Engineer · TCS

Enterprise AI retail optimization

  • Java Spring Boot microservices for constraint-based space optimization across 1,400+ stores and 1,000+ parameters.
  • Distributed search with Redis caching sustaining sub-200ms P95 across 2M+ SKU records.
  • Multi-tenant OAuth2 SSO with tenant-scoped claims across product modules.
  • Virtualized dashboard rendering for 100K+ SKU tables (~800ms to ~120ms).

Aug 2024 — May 2026

M.S. Software Engineering · San Jose State University

  • Research Assistant, Agentic AI Systems (Sep 2025 — May 2026): planner-executor agents evaluated on tool-call accuracy, schema adherence, and error recovery.
  • Teaching Assistant, Deep Learning (CMPE 258) and Data Mining (CMPE 255) (Aug 2025 — Apr 2026), two semesters.

Jun 2014 — Apr 2018

B.Tech Computer Science and Engineering · GITAM University

Hiring for SWE or AI engineering?

On OPT, based in San Jose, open to on-site, hybrid, or remote across the US. Prefer email — I reply within a day.

Email meResume