Shobhnik Wadhwa profile photo 1 on Tal

Shobhnik Wadhwa

Software Engineer • Backend/ai • Designing scalable, reliable AI agents and systems that get real work done

Gurugram

2+ years of work experience

Xane AI
Jan 202610 mosPresent

Gurugram, Haryana, India

󠁯•󠁏 Designed and implemented end-to-end system architectures, database schemas, and REST APIs, along with technical documentation and AWS deployment plans for the core product and its microservices. •󠁏 Built a multi-tool search agent using DeepAgents (LangChain) with persistent memory via Mem0, backed by hybrid retrieval over Qdrant using BGE-M3 embeddings and Reciprocal Rank Fusion (RRF). •󠁏 Engineered a document ingestion pipeline handling OCR (MinerU), Markdown-aware chunking, and vector embedding, with image contextualisation for multimodal retrieval. •󠁏 Explored emerging open-source models, tools, and frameworks, and built multiple internal tools and POCs to validate their fit into existing workflows, including RAGAS-based evaluation of RAG accuracy.
Roger (YC S24)
May 20261 moMay 2026

Austin, Texas, United States

• Built an agent that learns your brand through its website and social presence, then turns that information into brand creatives and UGC-style ads with automated Meta Ads deployment, taking ad generation from days to under 10 minutes. • Solely responsible for building, validating, and iterating on the overall product workflow from concept to working demo.
Otomashen
Jan 20251 yr 1 moJan 2026

Noida, Uttar Pradesh, India

󠁯•󠁏 Built and scaled a high-throughput EDI/X12 processing engine handling 20K+ claim files and millions of encrypted denial records which automated the entire pipeline to track the denial records. 󠁯•󠁏 Optimized backend services in Node.js/TypeScript with query tuning, indexing, and caching, reduced API latency from 10s → <1s at scale. 󠁯•󠁏 Engineered a real-time dispatch system for proximity-based doctor matching, request lifecycle (accept/decline), and instant notifications. 󠁯•󠁏 Delivered 4 production-grade client systems, led one end-to-end as Lead Developer, owning architecture and execution.
Stealth AI Startup (YC backed)
Aug 20246 mosJan 2025

San Francisco Bay Area

󠁯•󠁏 Owned the product end-to-end as the sole engineer, building all frontend workflows and integrating backend APIs from design to production. 󠁯•󠁏 Architected the complete backend system, designing scalable architecture, database schema, and core processing workflows. 󠁯•󠁏 Built a high-throughput notification pipeline using Node.js/TypeScript, BullMQ, Redis, PostgreSQL, and Socket.io, delivering thousands of notifications per second, implemented vector search for fast large-scale retrieval. 󠁯•󠁏Developed a production-grade AI agent using LangGraph, LangChain, and Gemini for complex workflow automation. 󠁯•󠁏Scaled the platform to 200–250 active users managing 500K+ production records in production.
GitHub
@shobhnik13
Personal portfolioshobhnik.site

Shobhnik’s AI Stack

anthropic apis
anthropic apis
claude code
claude code
claude
claude
codex
codex
langchain
langchain
langgraph
langgraph

Education

Maharaja Agrasen Institute Of Technology, Delhi

Bachelor of Technology - BTech, Information Technology

Maharaja Agrasen Institute Of Technology, Delhi

Join Shobhnik and 10k+ other professionals on

Tal Boss

Tal is the app where bosses meet engineers & builders directly, without middlemen

Download Tal Boss

Shobhnik Wadhwa on Tal

Headline

Software Engineer • Backend/ai • Designing scalable, reliable AI agents and systems that get real work done

About

Backend and AI engineer. I focus on the parts that still need a human mind: system architecture, breaking down hard problems, and rigorous code review. A lot of my code now is agent written. My job is making sure it's actually good. ~2 years in. Shipped things, broke things, got better at both

Location

Gurugram

AI stack

anthropic apis

claude code

claude

codex

langchain

langgraph

Work experience

Software Engineer (Backend & AI) at Xane AI, Jan 2026 - Present · 10 mos, Gurugram, Haryana, India, 󠁯•󠁏 Designed and implemented end-to-end system architectures, database schemas, and REST APIs, along with technical documentation and AWS deployment plans for the core product and its microservices. •󠁏 Built a multi-tool search agent using DeepAgents (LangChain) with persistent memory via Mem0, backed by hybrid retrieval over Qdrant using BGE-M3 embeddings and Reciprocal Rank Fusion (RRF). •󠁏 Engineered a document ingestion pipeline handling OCR (MinerU), Markdown-aware chunking, and vector embedding, with image contextualisation for multimodal retrieval. •󠁏 Explored emerging open-source models, tools, and frameworks, and built multiple internal tools and POCs to validate their fit into existing workflows, including RAGAS-based evaluation of RAG accuracy.

Product Engineer at Roger (YC S24), May 2026 - May 2026 · 1 mo, Austin, Texas, United States, • Built an agent that learns your brand through its website and social presence, then turns that information into brand creatives and UGC-style ads with automated Meta Ads deployment, taking ad generation from days to under 10 minutes. • Solely responsible for building, validating, and iterating on the overall product workflow from concept to working demo.

Software Engineer at Otomashen, Jan 2025 - Jan 2026 · 1 yr 1 mo, Noida, Uttar Pradesh, India, 󠁯•󠁏 Built and scaled a high-throughput EDI/X12 processing engine handling 20K+ claim files and millions of encrypted denial records which automated the entire pipeline to track the denial records. 󠁯•󠁏 Optimized backend services in Node.js/TypeScript with query tuning, indexing, and caching, reduced API latency from 10s → <1s at scale. 󠁯•󠁏 Engineered a real-time dispatch system for proximity-based doctor matching, request lifecycle (accept/decline), and instant notifications. 󠁯•󠁏 Delivered 4 production-grade client systems, led one end-to-end as Lead Developer, owning architecture and execution.

Product Engineer at Stealth AI Startup (YC backed), Aug 2024 - Jan 2025 · 6 mos, San Francisco Bay Area, 󠁯•󠁏 Owned the product end-to-end as the sole engineer, building all frontend workflows and integrating backend APIs from design to production. 󠁯•󠁏 Architected the complete backend system, designing scalable architecture, database schema, and core processing workflows. 󠁯•󠁏 Built a high-throughput notification pipeline using Node.js/TypeScript, BullMQ, Redis, PostgreSQL, and Socket.io, delivering thousands of notifications per second, implemented vector search for fast large-scale retrieval. 󠁯•󠁏Developed a production-grade AI agent using LangGraph, LangChain, and Gemini for complex workflow automation. 󠁯•󠁏Scaled the platform to 200–250 active users managing 500K+ production records in production.

Education

Bachelor of Technology - BTech, Information Technology, Maharaja Agrasen Institute Of Technology, Delhi

Public links

github: https://github.com/shobhnik13

shobhnik.site: https://shobhnik.site/