Hey, I am Yash
AI, full-stack, and systems. always building.
I am an AI-fueled full-stack engineer passionate about building systems that scale and ship fast. Currently, I am a Software Development Engineer at Binocs, Bangalore, where I build production AI agents, automate workflows with LLMs, and ship end-to-end features from infrastructure to UI. I reduced Claude API cost by 99% ($1.00 → $0.01 per slide) by redesigning the AI presentation pipeline with prompt chaining and structured outputs.
Previously, I was a Software Engineering Intern at ViewR, where I built a cross-platform desktop app with Electron + React spanning 5 microservices, implemented real-time ONVIF/RTSP video streaming at sub-100ms latency, and deployed 4 AI/ML models for attendance and face recognition reaching 98%+ accuracy on 10,000+ daily requests.
I also did research at IIT Mandi, improving continuous authentication accuracy for banking apps from 89% to 92%, and analyzing molecular olfaction using Graph Neural Networks across 15,000+ pharmaceutical compounds.
I am a final-year B.Tech CS student at IIIT Una (GPA 8.3/10, graduating July 2026). I keep building in public — follow along on my GitHub and LinkedIn.

Experience
Where I've worked.
- Reduced Claude API cost by 99% ($1.00 → $0.01/slide) by redesigning the AI pipeline with prompt chaining
- Shipped 5+ production AI agents with human-in-the-loop orchestration
- Launched full-stack admin dashboard in 24 hours (React + FastAPI + Terraform + K8s) serving 40+ users
- Integrated Stripe payments across 3 microservices with zero transaction failures
- Cut dev environment costs 40% via infrastructure and CI/CD optimization
- 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
Recent projectsGitHub ➔
Things I have built recently.
Serving 1,000+ monthly users with AI-powered resume suggestions. 99.9% uptime on AWS.
Sub-50ms move propagation, ELO-based matchmaking, OAuth login, containerized deployment.
Achievements
Competitions and contests I have placed in.
- 267th Global Rank — HackerRank AI Agent Challenge (12,885 participants)· May 2026
- 4th Place — HD Cryptocurrency Wallet with Biometric Auth Hackathon (50+ teams)· Feb 2025
- Top 4 — AlgoUniversity Contest (200+ participants) · ₹2,000 prize· Feb 2024
Tech depthAll projects ➔
What I build with and specialize in.
Writings and LearningsFull archive ➔
Essays on AI agents, full-stack systems, and building in public.