Portfolio

Sheshasaibaba Gujjari

Senior Full Stack Engineer & AI Specialist

Senior Full Stack Engineer with 7 years of experience at the intersection of enterprise-grade stability and AI automation — from Java/Spring ecosystems to TypeScript frontends and RAG pipelines.

Sheshasaibaba Gujjari — portrait photo

About

I am a Senior Full Stack Engineer with 7 years of experience situated at the intersection of enterprise-grade stability and cutting-edge AI automation. My career has been defined by a transition from building high-concurrency Java/Spring Boot ecosystems to architecting modern, high-performance TypeScript frontends and RAG-integrated AI pipelines.

  • Efficiency architect

    I specialize in finding data-intensive bottlenecks and reducing operational overhead — historically by as much as 70% — through custom automation tools and cloud-native architectures.

  • Full-spectrum engineering

    From provisioning automated pre-production environments on Azure/AWS to delivering WCAG-compliant, accessible UIs for institutional clients like the Washington State Board (SBCTC).

  • AI integration

    I don’t just call APIs — I build data processing pipelines. Hands-on with training NLP workflows, manually structuring vector datasets for RAG, and deploying local LLMs for unstructured data problems.

Experience

Projects

TaxByNav

Zero-cost architecture — Cloud Run + Cloudflare, tuned for a true $0 ops footprint (cost optimization at the core).

Live production SaaS for tax filing and appointments: zero recurring infra spend while staying secure and scalable.

  • FastAPI
  • Next.js 16
  • PostgreSQL
  • Google SSO
  • Cloud Run
Full page

Neural-Vision Outfit Recommender

Ensemble CV + Flask API — cosine NN retrieval with demographic-aware search pruning.

A high-precision image recommendation engine that uses a multi-model ensemble for visual similarity, demographic markers, and occasion context.

  • Python
  • PyTorch
  • Flask
  • OpenCV
  • ONNX
  • InsightFace
  • Scikit-learn
Full page

SGI Handbook RAG Chatbot

Hybrid retrieval — dense + sparse vectors; math-aware grounding, not just API glue.

High-precision QA over the SGI Driver’s Handbook — hybrid retrieval to cut hallucinations and retrieval latency.

  • Python
  • LangChain
  • FAISS
  • Llama-3.1
  • FastAPI
  • RRF
Full page

BlockVeritas

Hybrid on-chain + IPFS — ~95% lower storage cost vs naive all-on-chain metadata.

Community-driven news verification dApp: Proof-of-Reputation voting and Sybil-resistant jury mechanics.

  • Solidity
  • Ethereum
  • IPFS
  • Pinata
Full page

Open to collaboration

Let's connect

Building the future, one line at a time. Whether you're shipping a product, scaling a team, or exploring something ambitious — I'd love to hear from you.