Hey, I am Yash

• Re-architected the 130-page CDD investment-deck pipeline as a dedicated microservice, hybrid AI + code flow (Claude fills HTML narrative placeholders, deterministic covers/TOCs/charts code-generated). Cut deck cost from $130–260 to ~$1.30 (99% reduction).
• Owned the LLM Engine: prompt routing, context assembly, schema validation, output normalization, Redis caching (~30% AI-call reduction), Claude/Gemini orchestration across reports, decks, admin and email workflows.
• Shipped Admin Panel + Deal Generator in 24 hours (React + FastAPI + RBAC + JWT + Apollo enrichment), 40+ internal users, zero production errors, supporting sales conversion incl. POINT Broadband.
• Launched the Fibre CDD vertical end-to-end in 7–8 days, backend, frontend, ingestion, geospatial mapping, opening a new commercial due-diligence revenue path.
• Built 60–70% of the Stripe international payments stack across 3 microservices (checkout, tax, geo-pricing, subscriptions, webhooks), zero transaction failures in production.
• Migrated transactional email from SendGrid → Amazon SES (IAM, identities, templates, smoke tests) as my first production project.
• Cut dev cloud spend from ~$3K to $1K–1.2K/month (~60%) via scheduled scaling on EKS/RDS with Terraform; kept envs recoverable in ~3 minutes. Cloudflare tuning reduced origin load ~20%.
• Built a QA regression agent (Python CLI/container) that diffs 15K–22K-line report JSONs for missing sections, numerical drift (±2% tolerance), and narrative changes, integrated with CI/Grafana.
• Rolled out Claude Code, OpenAI Codex, and Gemini CLI org-wide; WireMock POC for mock AI responses cut testing roundtrips. Compressed recurring product workflows from 3–4 days to ~1 day.
• Zero-downtime domain + Cloudflare security migration: DNS cutover, WAF hardening, HSTS, CSP, key rotation, audit logs.

• Built cross-platform desktop app with Electron + React spanning 5 microservices (DMG in 8 weeks)
• Real-time ONVIF/RTSP video streaming at sub-100ms latency
• Deployed 4 AI/ML models for attendance and face recognition: 98%+ accuracy on 10,000+ daily requests

• Improved continuous authentication accuracy from 89% → 92% for banking apps
• Analyzed molecular olfaction with Graph Neural Networks across 15,000+ pharmaceutical compounds

Problem: 800,000 Indian clinics run on 3-minute paper consultations, doctors forget patients the moment they leave, losing ~₹50K/month in follow-ups. Doxa is an AI scribe that listens to a 15-second Hinglish voice memo after each patient and turns it into a structured record + automatic follow-up SMS. Zero workflow change, no EMR. The startup I'm building now.

Problem: SRE work is mostly pattern-matching against past incidents, but engineers spend hours doing it manually at 3am. Pilot is a fleet of AI agents that triage incidents, parse logs, gate deploys, and audit infra hygiene, Claude-driven, runs against your real stack, escalates only when humans actually need to look.

Problem: cold-email tools either spray-and-pray (low reply rates, deliverability tanked) or require 30 min of manual research per prospect (doesn't scale). Outreach combines per-prospect research, AI-personalized copy, warm-up rotation, and reply tracking, campaigns that actually feel hand-written.

Problem: chess.com is bloated and Lichess UI feels dated to me. Built a clean multiplayer chess platform with sub-50ms move propagation, Redis-backed game state, ELO matchmaking, OAuth login, and containerized deploys. Real-time chess that just feels fast.

Problem: my photo work was scattered across Instagram, Drive, and an old Lightroom catalog. shots is a self-hosted portfolio for the street, portrait, and travel work I've shot across Bangalore and India, built so I own the canvas and the metadata, not a platform.

Problem: students keep losing job opportunities to ATS filters because they don't know what a 'good' bullet looks like. finalcv is an AI resume builder with ATS-tuned templates and Gemini-powered bullet rewrites tailored to the JD. 1,000+ monthly users, sub-second suggestions.