💼 AI Developer — Agrigate Network Limited
🎓 B.Sc. in CSE — East Delta University

Building Intelligent Systems & Deep Learning Solutions

Specializing in Edge Compilation, Parameter-Efficient Fine-Tuning (PEFT/LoRA), Unsupervised Anomaly Localization, and Production MLOps Serving Meshes.

# About Me

Bridging Deep Learning Research & Production Systems

I am an AI Systems & Machine Learning Engineer specializing in parameter-efficient fine-tuning (PEFT/LoRA), edge model compilation (INT8 PTQ/ONNX), grounded retrieval-augmented generation (RAG), and automated SRE telemetry diagnostics.

Currently developing vision pipelines, multimodal diagnostics, and telemetry infrastructure at Agrigate Network Limited. My focus is architecting end-to-end, low-latency microservices with clean API boundaries, rigorous statistical drift detection, and high-performance developer tooling.

# Research & Conference Papers

Peer-reviewed abstract acceptances and deep learning research contributions.

Conference Paper EFAST-2026

Low-Light Image Enhancement Using U-Net Architecture

Investigating deep learning segmentation and reconstruction networks for restoring feature detail and visual quality in ultra-low-light environments.

Accepted for EFAST-2026 Presentation
Conference Paper EFAST-2026

Unpaired Handwriting Style Transfer via CycleGAN

Generative adversarial translation framework for transferring complex handwriting characteristics across unpaired document datasets without ground-truth alignment.

Accepted for EFAST-2026 Presentation

# Core Engineering Skills

Edge Optimization

ONNX Runtime, INT8 PTQ Quantization, Graph Compilation, Latency Profiling

LLM Adaptation & PEFT

LoRA From Scratch, Rank Adaptation, Cross-Entropy Perplexity, Causal Attention

MLOps & Serving Mesh

Canary Traffic Splitting, Shadow Replay, Wasserstein Covariate Drift

Computer Vision

PatchCore Anomaly Detection, Sub-pixel Heatmaps, PostGIS Geospatial

# Featured Engineering Systems

Production-grade AI architectures, autonomous developer tools, RAG agents, and MLOps serving meshes.

LLM Serving 8.37x Speedup

PagedInfer

High-throughput LLM serving engine implementing paged KV-cache memory allocation and continuous iteration batching, delivering an 8.37x throughput gain over static batching.

PyTorch FastAPI SSE Paged KV-Cache Continuous Batching
Explore Source & Engine
Architecture Audit Mermaid.js

ArchLens AI

Autonomous system design review engine auditing architecture anti-patterns (SPOFs, unthrottled queues, unindexed queries) and synthesizing dynamic Mermaid.js flowcharts.

FastAPI OpenCV Mermaid.js React
Explore Source & Engine
Production SRE Wasserstein EMD

IncidentPulse AI

Autonomous SRE incident investigation engine calculating Wasserstein distance anomaly shifts across distributed telemetry, isolating blast radiuses, and outputting runbooks.

FastAPI SciPy EMD React Vite
Explore Source & Engine
Codebase Cartography AST Engine

RepoScope

Codebase decomposition and cartography engine extracting architectural layers, runtime sequence flows, entry-point manifests, and developer onboarding runbooks.

FastAPI AST Parser Mermaid.js React
Explore Source & Engine
Meeting Diarization Jira AI

SyncPilot

Multi-speaker conversational diarizer and talk-time analytics engine extracting consensus items, architectural decisions, and synthesizing structured Jira/Linear tickets.

FastAPI Diarization Jira API React
Explore Source & Engine
Duplex Voice AI 24kHz Audio

Vocalis

Real-time duplex voice virtual assistant integrating Web Speech API recognition, fast conversational reasoning, and streaming harmonic neural audio synthesis.

FastAPI Web Speech Audio WAV React
Explore Source & Engine
Mock Coach Rubric Scorer

EvalIQ

Autonomous mock technical interview coach evaluating verbal/text responses across 4 rubric dimensions and synthesizing adaptive probing follow-up questions.

FastAPI Speech-to-Text Rubric Engine React
Explore Source & Engine
Grounded RAG Citations

DocuAssist

Enterprise customer support RAG agent with hybrid dense/sparse vector retrieval, strict confidence hallucination guards, sub-2ms search telemetry, and verified source citations.

FastAPI Scikit-Learn TF-IDF React
Explore Source & Engine
MLOps & Mesh Canary + Drift

OpsFlow Engine

Multi-model registry and dynamic traffic router with SHA256 auditability, probabilistic Canary splitting (0–100%), zero-latency shadow replication, and Wasserstein covariate drift tracking.

FastAPI PyTorch SciPy EMD React
Explore Source & Metrics
Computer Vision Unsupervised

AnomaCore AI

Unsupervised industrial defect localization implementing the PatchCore framework, multi-scale convolutional memory banks, nearest-neighbor Euclidean distance scoring, and sub-pixel contour isolation.

PyTorch PatchCore OpenCV FastAPI
Explore Source & Metrics
PEFT & LLMs LoRA From Scratch

AdaptiForge AI

Custom Low-Rank Adaptation (LoRA) engine freezing base parameters while training low-rank A/B decomposition matrices on transformer projections, featuring live perplexity convergence tracking.

PyTorch Transformer PEFT FastAPI React
Explore Source & Metrics
Edge Optimization 1.83x Speedup

EdgeDeploy AI

Model optimization engine compiling PyTorch vision graphs into constant-folded ONNX binaries, executing dynamic INT8 Post-Training Quantization, and profiling p95 latency and MSE tensor drift.

ONNX Runtime INT8 PTQ PyTorch FastAPI
Explore Source & Metrics
Geospatial PostGIS ST_Contains

CTG_Shield_Spatial_Engine

Real-time geospatial danger-zone intelligence and proximity panic alert engine using PostGIS polygon indexing, dynamic risk decay scoring, and asynchronous WebSocket SOS broadcasting.

PostGIS WebSockets FastAPI Python Async
Explore Source & Metrics
Mobile & Telemetry Live SOS

CTG_Shield_Mobile

Mobile safety companion for the CTG Shield engine featuring background GPS telemetry, dynamic polygon containment alerts, one-tap emergency SOS broadcasting, and low-latency WebSocket synchronization.

Mobile UI WebSockets GPS Telemetry Geofencing
Explore Source & App
Security & Crypto Ed25519

Offline_QR_Ticket_Guard

Zero-network event admission engine using Ed25519 asymmetric cryptography and transactional SQLite replay ledgers to cryptographically prevent ticket forging and replay attacks.

Cryptography Ed25519 SQLite FastAPI
Explore Source & Metrics
Time-Series PatchTST

Deep_Temporal_Forecaster_AI

PatchTST-inspired PyTorch engine utilizing sub-series temporal patch tokenization and channel-independent self-attention for multi-step horizon forecasting and anomaly detection.

PyTorch Transformers FastAPI
Explore Source & Metrics
Vision Agents Grounding

Vision_UI_Navigator_Agent

Autonomous multimodal web navigation agent using visual grounding, DOM bounding box normalization, and asynchronous Playwright perception-action execution loops.

Playwright VLM Grounding Python Async
Explore Source & Metrics
RAG & Search FAISS Dense

ALO_Agri_RAG_AI

Domain-specific Retrieval-Augmented Generation pipeline built with FAISS vector indexing and SentenceTransformer embeddings for context-grounded advisory generation.

FAISS Transformers FastAPI
Explore Source & Metrics
Vision Telemetry YOLOv8

Crop_Weather_YOLO_Estimator

Computer vision microclimate estimator analyzing atmospheric clarity, RGB saturation distributions, and real-time bounding box detections.

YOLOv8 OpenCV FastAPI
Explore Source & Metrics
Multimodal Vision PyTorch

Crop_Guard_AI

Multimodal plant disease diagnostic pipeline fusing deep convolutional leaf feature maps with tabular soil chemistry and ambient environmental telemetry.

PyTorch Multimodal FastAPI
Explore Source & Metrics
Predictive Analytics Telemetry

Broiler-ai-project

Industrial telemetry and growth-curve analytics engine tracking feed conversion ratios (FCR), heat stress coefficients, and ambient ammonia risks.

PyTorch FastAPI Docker
Explore Source & Metrics

Contact & Collaboration

Available for software & AI engineering roles, research collaborations, and production system consulting.