REZINX
Transparent AI Solutions
Interactive Portfolio
Real-world AI systems built for production. Explore detailed case studies, live telemetry simulations, technical constraints, and measurable impact metrics.
AI Engineer & founder
AI engineer with three years of experience building production AI systems: LLM fine-tuning, RAG pipelines, and full-stack ML backends with complex optimization layers. I've worked as the sole engineer on end-to-end projects for international clients, handling everything from raw data to deployed services. B.Sc. Artificial Intelligence, COMSATS University Islamabad (CGPA 3.61).
"I care about the parts that don't fit on a slide: handling sparse and messy data, cutting inference latency, indexing high-dimensional vectors, and shipping services that hold up under real load, not just notebooks that run once."
Taxonomy-aware retrieval: embeddings organized around semantic hierarchies instead of raw objects, on a re-architected Qdrant layer, served by async FastAPI microservices. In one SaaS engagement: query time cut 3–5×, concurrency up ~8×.
A production price-elasticity optimization engine. Ingests catalog logs into Supabase, performs SKU demand forecasting using LightGBM, and passes predictions to a two-phase LP + SLSQP profit optimizer under margin floors and competitor guardrails. Includes champion/challenger WMAPE gating.
Custom model deployments for specialized clients. Led LoRA and QLoRA fine-tuning workflows for custom domain-specific generative models, automated model training pipelines on DigitalOcean droplets and physical GPU nodes, and shipped custom natural language and vision pipelines.
R&D · Applied Research
Self-directed builds where we test methods end to end before offering them to clients. Code is public.
Retail demand forecasting on M5 (30,490 store-item series) with data-calibrated routing for dense, intermittent, and sparse demand. Phases 1–3 complete: an objective bake-off where LightGBM Tweedie wins every dataset (WMAPE28 0.302 / 0.348 / 0.488 vs 1.000 for a zero forecast). 141 tests, bit-identical reruns. Agent layer (Agno) is next.
Real-time pose-based fall detection, hazard recognition, child-safety monitoring, and a RAG-powered first-aid guidance assistant (FAISS & BM25 hybrid search), with Firebase FCM push alerts. Built end to end: models, backend, and mobile app.
Engineering Case Studies
Not a list of job duties. Each item is a real engineering bottleneck we hit, what we built to resolve it, and the performance output it generated.
Embedding around semantic taxonomies instead of raw objects, plus a re-architected Qdrant layer.
Async request handling lifted a hard concurrency ceiling without rewriting the models.
The optimizer doesn't scan every price. A two-phase LP + SLSQP search explores a bounded band around each SKU's current price (shaded), under margin floors and competitor caps, to maximize profit, not revenue. Demand falls as price rises; profit peaks where volume and margin trade off, and turns negative below unit cost.