Kanav Chauhan
AI full-stack developer
kanavchauhan08@gmail.comGitHub @Kanav-ChauhanLinkedIn in/kanavchauhan001X @kanavchauhan001
Experience
- Apr 2026 to now
AI full-stack developer, Toshi Consulting Services
- Sep 2025 to Mar 2026
Independent AI developer: Atlas, Support AI
- 2023 to 2024
Google AI & ML intern, AICTE
Selected projects
Toshi CRM (Sep 2026, AI full-stack developer at Toshi Consulting)
A sales CRM built for Indian B2B teams: leads from IndiaMART, JustDial and Meta Ads in one queue, an AI sales assistant, WhatsApp follow-ups and GST-correct quotes. 15 min to call every new lead, with a timer, 2 min to a GST-correct quote, 3 languages Priya speaks on calls. Live site: crm.toshiconsulting.com
Agri Warehouse (Jul 2026, AI full-stack developer at Toshi Consulting)
AI-checked grain intake for agricultural warehouses: a vision model checks every truckload, every bag gets a QR code, and certificates are signed so nobody can fake them. 1 QR code on every bag, gate to dispatch, 100% of truckloads checked by the vision model, 2 languages, English and Hindi. Pilot site: warehouse.toshiconsulting.com
ExamPrep (May 2026, AI full-stack developer at Toshi Consulting)
An exam preparation platform for classes 1 to 12: adaptive practice, mock tests, an AI doubt-solving tutor and a study plan that rebuilds itself after every test. 12 school classes covered, 1 to 12, 9 league tiers that keep students practising, 3 platforms: web, Android and iOS. Live site: examprep.toshiconsulting.com
Support AI (Mar 2026, Solo build: AI pipeline, backend, web app)
A multi-tenant support platform: AI classifies tickets from email and WhatsApp, finds the right help articles and drafts cited replies, and a human approves anything risky. 207 backend tests passing, 29 web pages in the app, 5 roles, from owner to viewer. Live demo: p2.kanav.space
Atlas (Sep 2025, Solo build: backend, retrieval, evals, web app)
Company knowledge search that answers employees' questions with citations, using only the documents each person is allowed to see. 0 permission leaks in every eval run, 64 question eval set, LLM-judged, 182 API tests passing. Live demo: p1.kanav.space
Skills
- LLMs & AI agents: Claude API, OpenAI API, Groq API, LangChain, AI agents & tools, MCP
- RAG (Retrieval-Augmented Generation): RAG pipelines, pgvector, Hybrid search, Re-ranking, Embeddings
- Evals & safety: Eval suites, LLM-as-judge, Human approvals, RBAC & tenancy, Tracing & costs
- Backend: Python, FastAPI, Django & DRF, PostgreSQL, Redis, JWT & auth
- Frontend: TypeScript, React, Next.js, Tailwind CSS, Three.js, GSAP
- Infra & data: Docker, GitHub Actions, Caddy, LiteLLM gateway, n8n, Pandas & NumPy, Scikit-learn
Education
B.Tech CSE, AI & ML specialisation, SRM University, 2025
Certifications
- Google AI & ML Internship, AICTE