AI Agents · LLM Finetuning · Inference Engineering — from research to production GenAI at scale.
Multi-agent pipeline — Engagement → Gatherer → Synthesis — that auto-generates editable PowerPoint Quarterly Business Reviews. Reduced QBR prep from days to minutes.
Hierarchical Marketing Mix Model with adstock, saturation curves and JAX-accelerated MCMC. ROI-optimised budget allocator with GPT-generated scenario narratives.
Transformer-based model combining internal inventory signals with NLP-processed news feeds to detect pharmaceutical supply chain disruptions weeks in advance.
XGBoost + ALS for retention/cross-sell with E2E AWS SageMaker deployment and OpenAI explanations for sales teams.
CrewAI multi-agent system (Researcher → Writer → Reviewer) generating curated ML study notes on demand.
Generate-fix-execute loop producing interactive charts, tables, and insights from natural-language analytics queries.
Random Forest model deployed on SageMaker; improved conversion targeting for enterprise pharma sales reps.
CatBoost + ANN using flight and passenger features for a major US airline.
NLI pipeline using PubMedBERT on Databricks to automatically mine insights from pharmaceutical literature at scale.
Gaze estimation iOS app and driver safety demo using convolutional models.
Embedded systems and product engineering for automotive and broadcast technology domains.
A deep dive into three production model serialisation formats — performance benchmarks, security considerations, and a quick decision guide with conversion code recipes.
Read on Medium →End-to-end walkthrough of a hierarchical Bayesian MMM in PyMC — adstock transforms, saturation curves, and ROI optimisation.
Drafting…
Travel · Photography · Buddhism
Open to roles and collaborations. I usually reply within a day.
Or email directly: ankitwahane497@gmail.com