Jun–Aug 2026
India · Forward Deployed Engineer
I turn ambiguous customer
workflows into shipped
AI systems.
I work across technical discovery, solution scoping, prototypes, demo environments, and production handoffs—making AI systems useful for the people who need to adopt them.
60% fewer unqualified demos 80% less compliance work 99.9% availability
Customer delivery · 2026
PineBrook customer implementation
Made technical value legible in a fast, customer-ready demo and compliance workflow.60% fewer unqualified demos, three weeks shorter sales cycles, 80% less compliance documentation effort, and 3+ qualified enterprise opportunities.Product delivery · 2025
TexOS document workflows
A practical document workflow for teams moving between TeX and more than twenty formats.50+ weekly active users, 40% weekly activation improvement, 20+ formats, 99.9% availability, and 70% lower operating cost.Operations systems · 2025
Medikabazaar operations data
Moved a payout workflow from multi-day manual handling to an operational system teams could trust.Payout turnaround dropped from three days to under ten minutes across 400+ monthly transactions; 10,000+ records across 28 states supported a 35% reliability improvement downstream.Systems research · 2026
Cache Cliff edge-AI research
A hardware-aware way to choose vision encoders for edge visual-language systems.Vision encoders accounted for 70–85% of time-to-first-token; the Cache Cliff framework made hardware-aware trade-offs explicit.Where the work happened
From customer room to production system.
Jan–May 2026
Research Fellow
Edge AI systems researchBenchmarked eight vision architectures across four hardware platforms for edge visual-language workloads.Sep–Dec 2025
TexOS
Product & systems builderShipped a document workflow product serving 50+ weekly active users across 20+ formats.Let's make the hard part tractable