Portfolio

Sheshasaibaba Gujjari

Senior Full Stack Software Engineer

Canada (Remote-ready)

Senior Software Engineer with 7 years of experience bridging enterprise stability and modern AI automation. Specialized in transforming manual, data-intensive bottlenecks into scalable, cloud-native architectures through custom RAG pipelines and CI/CD automation.

Sheshasaibaba Gujjari, portrait photo

About

Senior Software Engineer with 7 years of experience bridging enterprise stability and modern AI automation. Specialized in transforming manual, data-intensive bottlenecks into scalable, cloud-native architectures through custom RAG pipelines and CI/CD automation.

  • 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 donโ€™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 for 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 with dense + sparse vectors, math-aware grounding, not just API glue.

High-precision QA over the SGI Driverโ€™s Handbook, using 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.