I got into AI in 2023, right when it became the word everyone used and for a while, just using GenAI felt like being an AI engineer. It wasn't, until I went back to fundamentals, decision trees to XGBoost in college labs, Kaggle nights... Then NLP, chatbots and my first hackathon wins, all while CS core kept me grounded. Working on real ground problems and publishing research taught me building isn't enough, explaining it clearly matters just as much.
That mix of curiosity and discipline is why I ended up, moving from prototypes to real agentic systems with LangChain and RAG, and now voice AI with Pipecat and LiveKit. I'm an AI engineer because I stayed with the unglamorous parts long enough to actually lead in them, not because AI is trending.
I'm an AI/ML engineer who builds systems end to end from the data pipeline to the model to the API that serves it. My path into this field wasn't a straight line into GenAI; it moved step by step classical ML models, then rule-based NLP chatbots, then multi-agent systems and now voice AI. Each stage changed how I think, from writing functions to designing systems.
That progression is also why I don't reach for an LLM by default. Some problems just need an engineer who looks closely enough to find the simpler answer — a rule, a retrieval step, a piece of logic the model wouldn't suggest on its own. I care about that judgment as much as the building itself, because I believe AI can genuinely help across far more domains than it currently touches and getting there takes engineers willing to do the unglamorous, structural work first.
Solving real problems is the part I love most. Everything else the frameworks, the papers, the leaderboards is in service of that.
- 2nd place, IndiaAI × IBM GenAI Hackathon — ranked among 6,000+ competing teams
- Grand Finalist, Meta × PyTorch OpenEnv Hackathon — top 800 of 31,000+ teams, multi-agent RL system built in 36 hours
- Published Researcher, ICETIS 2026 — TA-RAG, reduced RAG hallucination rate from 20% to 8%
- Published Researcher, IRJAEH 2025 — CropGuru AI, ML-based crop recommendation framework for Indian agriculture
- 4-star Python Coder, HackerRank — verified problem-solving track record
- Kaggle Contributor — ranked, with medals earned on submitted work
- Cybersecurity Internship, AICTE-EduSkills × Zscaler — completed with Grade Outstanding
- 9.10 CGPA, B.Tech AI & ML — with Honours in Cloud Computing and a Minor in Robotics
- Co-Lead, GDG On Campus for AI/ML — building and mentoring a student ML community
|
The obvious build: dump regulations into a vector DB, wrap an LLM around it. I didn't because in RBI/SEBI/GST compliance, a hallucination that sounds well-sourced is more dangerous than an obvious error. What I built instead: a hybrid system where the LLM never decides, it only explains what a rule engine already decided. |
flowchart TD
Q[User query] --> R{Rule engine:<br>deterministic?}
R -->|Yes| RE[Apply known rule]
R -->|No| RAG[Retrieve via ChromaDB]
RE --> EXP[LLM: explain only]
RAG --> EXP
EXP --> OUT[Answer + audit log]
OUT --> SQL[(Immutable<br>SQLite trail)]
|
Why this took longer to build — and why that was the point
Encoding known regulations as deterministic rules is slower than letting an LLM "figure it out." But an MSME acting on bad compliance advice faces real fines. The rule engine handles what's actually deterministic across RBI, SEBI, GST, MCA, and Labour frameworks; RAG handles document lookup where rules don't cover it; the LLM's only job is turning a decision into plain English. Every decision is logged to an immutable audit trail because "trust me" isn't an audit strategy.
FastAPI ChromaDB SQLite · → github.com/Vedika-Sd/ComplianceOS-v1
Published · ICETIS 2026
Most RAG pipelines answer even when they shouldn't. I spent most of the engineering effort on the unglamorous part: making the system refuse correctly.
| Metric | Before | After |
|---|---|---|
| Hallucination rate | 20% | 8% |
| Out-of-scope rejection | 5% | 90% |
Why "rejection rate" is the metric that mattered
Anyone can tune a RAG pipeline to answer more confidently. Getting it to correctly say "this is outside what I know" 18× more often without becoming useless-cautious on in-scope questions is the harder, less celebrated problem. It's the one that matters if the system ever touches a real financial decision.
Standard forecasting assumes clean seasonality. Real dairy sales in Maharashtra spike around 46 regional festivals no off-the-shelf model has heard of and no single algorithm wins across every product type.
flowchart LR
S[35 SKUs, 5yrs daily sales] --> Router{4-segment<br>product router}
Router --> P[Prophet]
Router --> SX[SARIMAX]
Router --> XG[XGBoost]
Router --> CR[Croston's<br>intermittent demand]
P & SX & XG & CR --> OUT[7.0% volume-weighted WAPE]
Hand-built the 46-festival demand calendar, no library had one. Served via FastAPI with a model registry.
Python Prophet SARIMAX XGBoost · → github.com/Vedika-Sd/Demand-Forecasting
Most churn projects stop at reporting ROC-AUC. This one ships an explanation with every prediction — SHAP integrated directly into the API response, so a business user sees why a customer is flagged, not just a probability.
| ROC-AUC | 0.79 |
| F1-optimized threshold | 0.61 |
| Training data | 50K real banking records |
| Response time | sub-second, containerized, live on Render |
Actually try it:
curl -X POST https://[indian-bank-churn-prediction-ml-system.onrender.com]/predict \
-H "Content-Type: application/json" \
-d '{"customer_data": "..."}'LightGBM SHAP FastAPI Docker · → github.com/Vedika-Sd/Indian-Bank-Churn-Prediction
| Your problem involves... | Look at |
|---|---|
| Regulated / high-stakes domains where wrong answers cost money | ComplianceOS, TA-RAG |
| Forecasting with messy, non-standard seasonality | Demand Forecasting |
| Production ML that has to explain itself | Churn Prediction |
| Multi-agent systems under time pressure | StratArena — built in 36hrs, top 800 of 31,000+ teams |
Proof, for the skeptical (achievements & publications)
- 2nd place, 6,000+ teams — IndiaAI × IBM GenAI Hackathon — StartupSarthi, agentic compliance assistant
- Top 800 of 31,000+ teams — Meta × PyTorch OpenEnv Hackathon — StratArena, multi-agent RL with Theory-of-Mind opponent modeling, built in 36 hours
- Published, ICETIS 2026 — TA-RAG, hallucination reduction in regulatory RAG
- Published, IRJAEH 2025 — ML-based crop recommendation framework for Indian agriculture (DOI 10.47392/IRJAEH.2025.0472)