PatchPilot
AI-powered DevSecOps platform scanning 500+ files with SAST, dependency, and secret-detection tools. LLM inference optimized to under 150ms.
[ GENERATIVE AI ENGINEER ]
I don't just use AI. I architect it.
B.Tech AI student at SRM Institute, building end-to-end GenAI systems from RAG pipelines to LLM inference optimization. Google Certified Generative AI Professional. AWS ML Specialty. 4 production-grade AI systems shipped. Seeking Generative AI / ML Engineer internship.
production-grade builds, measured by latency, relevance, and reliability
AI-powered DevSecOps platform scanning 500+ files with SAST, dependency, and secret-detection tools. LLM inference optimized to under 150ms.
RAG-based GenAI system with 90%+ answer relevance. Prompt optimization + model fine-tuning on domain data. Handles 100+ concurrent queries at sub-200ms retrieval.
Threat detection system achieving 92% F1-score across 50K+ network records. Deployed on AWS EC2 with Docker. 99.5% uptime over 3 months.
Churn prediction with 85% accuracy after analysis of 10K+ customer records. Benchmarked LR, RF, and XGBoost. Automated ML pipeline cutting preprocessing time by 50%.
signals from clubs, open source, research, and credentialed work
Ranked #5 out of 42,000+ contributors globally in GirlScript Summer of Code — the largest open source program in India. Contributed across multiple repositories with high-impact PRs, code reviews, and community mentoring.
B.Tech in Artificial Intelligence | GPA: 8.8/10 | 2024–2028
Plus AWS ML Specialty, Accenture AI, CISCO Data Science, JP Morgan SWE, Deloitte & TCS GenAI
LangChain integration examples & RAG utilities on GitHub
Presented RAG architectures and model fine-tuning to faculty and peers at SRM
tools arranged as working nodes, not buzzword confetti
[ OPEN CHANNEL ]
I'm actively seeking Generative AI and ML Engineer internships. If you're working on something that pushes the limits of what AI can do, I want to hear about it.