AI Engineer · Production Systems · Delhi NCR, India
I’m Abhishek. I build the systems behind modern AI products—from inference and evaluation to context engineering and backend architecture—so they remain reliable in production.
10+ years building production software · Serving users in 85+ countries
Independent research · 2026
I tested whether small recurrent models could solve deeper graph problems by taking more steps. Extra steps improved partial predictions, but a shortcut in my graph generator leaves the reasoning claim unresolved.
I enjoy building software that survives real users.
I joined AssessPrep as one of its first engineers in 2016. Over nine years, I moved from frontend to backend, infrastructure, and AI while helping the platform grow to serve users in more than 85 countries.
Today I spend most of my time improving the reliability, latency, and evaluation of production AI systems. I’m particularly interested in context engineering, inference efficiency, and the tooling that helps teams ship AI safely. Outside the day-to-day work, I’m usually testing an inference idea or reading AI systems research.
Production AI · AssessPrep
Developed and deployed fine-tuned models for automated assessment grading and content recommendations, including evaluation, lifecycle monitoring, and the MLOps pipelines needed to update them safely. Also built NLP systems for question analysis and an in-house RAG support bot.
Infrastructure · AssessPrep
Helped split the monolith into Kubernetes-based services, automate infrastructure and delivery with Terraform and CI/CD, and add monitoring and autoscaling. Teams could deploy services independently and scale the parts under load.
Read the case study →Working with Go · Python · Node.js · Kubernetes · Terraform · AWS/GCP
Good AI products are reliable before they’re clever, measured before they’re optimized, and useful before they’re impressive.
In a three-file Python project, cross-file symbols improved edits across six functions. On 20 SWE-bench Lite issues, supplying file paths improved file selection. Full source context helped most, while my learned encoder failed.
Read →PHP2Shell, a Node.js RCE, a poisoned LiteLLM release, compromised eMudhra CA keys, a huge Oracle patch drop, two exploited zero-days, and now Linux kernel and BIND DNS bugs, all within about 48 hours. What each one means, who is affected, and a checklist you can actually skim.
A browser-based video editor that runs entirely client-side using FFmpeg compiled to WebAssembly — no uploads, no servers, full privacy.