Portrait of Avinash Kumar Shudhanshu

Avinash Kumar Shudhanshu

Software Engineer @ Google | Gen-AI | Lead | Backend | Architect | WSE | Full-Stack | Polyglot | ML | RAG | Stanford | DU

I’m a Lead Software Engineer/Architect focused on backend and full-stack systems, with hands-on delivery in Gen-AI, RAG, cloud-native services, and scalable product engineering across enterprise and consumer contexts.

Email: avinashsudhanshu@gmail.com Location: India
View Resume Explore Experience
7+ YearsEngineering Experience
5 RolesAcross Product Domains
Gen-AI + RAGProduction Delivery
AWS • Azure • GCPCloud Engineering

Academic Profile

Education details aligned to the latest resume format.

Degree Year Major Institution
M.Sc. Informatics 2019 Information Technology and Computer Networks University of Delhi
B.Sc. Electronics 2017 Electronics and Communication University of Delhi

Work Experience

Total Experience: 7 Years

Web Solutions Engineer — Google, Bengaluru, Karnataka, India (Hybrid)

Jul 2026 – Present | Domain: Digital Support Experience | Full-time

Key contributions
  • Design, build, and scale AI agents and intelligent automation tools that optimize operations and improve the Google Cloud support experience.
  • Architect and deploy context-aware AI agents using Google internal LLM frameworks and Gemini APIs to automate complex support workflows and reduce resolution times.
  • Develop robust full-stack automation tools and internal supportability platforms across Google Cloud Platform, modern JavaScript/Python frameworks, APIs, and cloud-native databases.
  • Partner with Supportability, Strategy, and Engineering teams to translate complex business requirements into reliable, production-grade applications.
  • Focus on scalability, supportability, testing, and continuous deployment to establish reusable engineering practices for internal platforms.

Technical Lead — Carlyle Group (Vichara), Remote, India

Feb 2026 – july 2026 | Domain: Investment Banking | carlyle.com

Key contributions
  • Architected a benchmark-driven pricing engine integrating Snowflake and Postgres to automate scalable, audit-grade market yield computation with AI-assisted validation and financial time-series analytics.
  • Designed cross-system data architecture for weighted benchmarks, versioned compositions, and dynamic rate resolution (WA yield, illiquidity premium, risk adjustments) with caching and batch optimisation.
  • Built high-performance analytics pipelines and Snowflake service layers enabling idempotent ingestion, data quality controls, and anomaly-aware coverage tracking.
  • Preserved backward compatibility by decoupling AI-enabled discount-rate resolution from legacy cashflow models, ensuring deterministic and regression-safe valuations.