AI Engineer
AI Engineer specialising in agentic systems, RAG applications and LLM workflows.
<coder>
Full-stack developer who writes clean, production-ready code — React, Node.js, Flask.
AI Engineer Intern @ ReadyForRole · Bangalore
> Agentic AI
I'm Bhaskar Pandit M N (ಭಾಸ್ಕರ್ ಪಂಡಿತ್) — an AI Engineer who turns disorder into working systems: agentic AI, LLM applications, RAG pipelines and full-stack products that hold up in the real world. Currently building production AI at ReadyForRole Pvt Ltd; previously teaching machines to catch faulty sensors at DRDO GTRE.
01 — About
I build things that think. Right now that means agentic AI systems, RAG applications and knowledge assistants at ReadyForRole Pvt Ltd — LLM workflows that don't just demo well, but survive real users in production.
Before that, I spent time inside GTRE (DRDO) — India's gas-turbine research establishment — training machine learning models to validate sensor data, identify faults and predict maintenance before things break. Aerospace research teaches you one thing fast: a model that's almost right is wrong.
As Co-Founder & Director of KLS Tech Solutions, I've shipped products end-to-end — like LokSuraksha, a citizen safety platform — from architecture to deployment. Between the research rigor and the startup speed sits the work I like most: turning messy problems into systems people actually use.
Off the keyboard, I captain my college cricket team and have played state-level cricket for Karnataka. Leading on the pitch and designing systems share the same core skill: finding order in chaos.
02 — Experience
ReadyForRole Pvt Ltd
Building production AI end-to-end: agentic AI systems that reason and use tools, RAG applications over real knowledge bases, LLM workflows and knowledge assistants — shipped as full-stack products, not notebooks.
DRDO GTRE · Bangalore
Applied machine learning to aerospace test data at India's premier gas-turbine research establishment — validating sensor streams, identifying faults, and building the data-quality groundwork for predictive maintenance. Where a model that's almost right is wrong.
M.S. Innovations · Part-time, Remote
Developing software solutions in a fully remote, delivery-focused environment — balancing production work alongside defence research.
KLS Tech Solutions · Remote
Directing technical development and software delivery strategy. Leading cross-functional teams to ship products end-to-end, including LokSuraksha, our citizen-safety reporting platform.
Next Gen 3.0 · Bengaluru
Intensive hands-on immersion in full-stack web development — from front-end design through back-end implementation.
03 — Projects
Real systems with real users in mind — each one built problem-first.
Exam aspirants juggle multiple competitive exams with generic, one-size-fits-all prep schedules — and no way to adapt plans to their own pace and syllabus.
A full-stack platform that generates personalized study plans using GPT-3.5 — prompt-engineered LLM pipelines turn a student's exams, dates and inputs into an actionable schedule.
React + Material UI frontend on Vercel, Flask REST API on Render, SQLite persistence, OpenAI API integration — a cleanly separated, independently deployed client/server system.
Deployed and live — turns hours of manual schedule planning into a single prompt-driven flow, with plans that adapt to each student's exams, dates and pace.
Civic hazards — broken infrastructure, unsafe zones — go unreported because there's no low-friction channel between citizens and the authorities who can act.
An end-to-end reporting system: a mobile app for GPS-tagged hazard reports with photos, and a web admin dashboard for authorities to triage, track and resolve them.
React Native (Expo) mobile client, Node.js backend, and an admin web dashboard — one API serving two clients, built and led at KLS Tech Solutions.
A working civic-tech pipeline from citizen to authority: report in seconds, triage in one dashboard — built and led as a startup product, not a class project.
Real-time, cross-media deepfake detection platform that flags AI-generated scam content across images, audio and video.
Wearable assistant for the visually impaired: AI object detection with real-time voice output, running on an ESP32-CAM.
Women's safety SOS system that works where the internet doesn't — emergency alerts over SMS for remote and low-connectivity areas.
Automated attendance using facial recognition on live camera feeds — no roll calls, no proxies.
More experiments and work-in-progress on github.com/BhaskPand →
04 — Skills
05 — Beyond Code
Played state-level cricket for Karnataka (2020) and awarded "Best Sportsman of the Year". Now captain of the APSCE college cricket team, with university-level match experience.
Coordinator of the ALGO Club at APSCE — organizing hackathons and running Git & GitHub sessions for students.
Team Head of the APSCE Music Society. I play 8 instruments — Mrudangam, Guitar, Flute, Ukulele, Kanjira, Djembe, Ghatam and Veena.
06 — FAQ
An AI Engineer and Full-Stack Developer based in Bangalore, India. Currently an AI Engineer Intern at ReadyForRole Pvt Ltd building agentic AI systems, RAG applications and knowledge assistants. Previously a Research Intern at DRDO GTRE working on sensor validation and predictive maintenance with machine learning, and Co-Founder & Director of KLS Tech Solutions.
Production AI systems: agents that reason and use tools, RAG pipelines over real knowledge bases, LLM-powered applications, computer-vision systems, and the full-stack layer — React, Node.js, Flask — that turns models into products. Highlights include ExamsAI (live LLM study planner), LokSuraksha (citizen safety platform), and InSight AI (edge-AI smart glasses on an ESP32-CAM).
Every system tends toward disorder — the job of an engineer is to spend energy pushing back. Most of what I do is exactly that: taking chaotic inputs — messy sensor data, ambiguous prompts, half-formed product ideas — and turning them into systems that behave predictably. Chaos in, order out.
Yes — for AI engineering roles, agentic/LLM product work, and interesting collaborations. The fastest way to reach me is bhaskarpanditmn@gmail.com.
07 — Contact
An AI product to build, a system to untangle, or a role you think I'd be a fit for — my inbox is open.