Skip to main content

// Senior Data Science Specialist & AI Researcher

Arnol P S

Building production AI systems at the intersection of Computer Vision, Deep Learning, and Vision-Language Models.

Arnol P S

About Me

I'm a Senior Data Science Specialist with 5+ years of experience designing and deploying production-grade AI/ML systems across Computer Vision, NLP, and Generative AI.

I build multi-agent architectures, hybrid RAG pipelines fusing vector and graph databases, and real-time conversational AI platforms. My work spans the full stack — from semantic chunking and embedding pipelines to LLM guardrails and production observability.

I've led patent-pending research on biometric identification using DINOv2 feature extraction and wavelet-based image enhancement, achieving 92% accuracy with novel computer vision techniques.

Shout-Out Award
ISO 42001:2023 Recognition

Received Shout-Out award for contributions to AI Management System documentation and preparedness for the ISO 42001:2023 surveillance audit.

Experience

Professional journey in AI/ML and Data Science

Aug 2025 – Present Current Reflections Info Systems Pvt. Ltd.

Senior Engineer - Data Science

Reflections Info Systems Pvt. Ltd.

Leading R&D of AI-powered enterprise solutions spanning multi-agent architectures, hybrid RAG systems, and real-time conversational AI.

  • Built multi-agent log analytics platform with 4-agent event-driven pipeline processing 10K+ daily logs
  • Designed hybrid RAG system fusing Qdrant vector search, Neo4j graph traversal, and Reciprocal Rank Fusion ranking
  • Implemented 5-layer security pipeline with LlamaGuard content safety, PII sanitization, and prompt injection prevention
  • Architected real-time WebSocket streaming with buffer-then-sanitize pattern for secure LLM output delivery
  • Built Vision-Language Model pipelines for multi-format document extraction with provider failover
  • Built agentic outreach platform with MCP server architecture, multi-phase LLM workflows, and template-driven document generation
  • Contributed to ISO 42001:2023 AI Management System surveillance audit - received Shout-Out award for documentation quality
Dec 2024 – Jul 2025 Digital University Kerala

Senior Data Scientist - Consultant

Digital University Kerala

Led research initiatives in computer vision and NLP, including patent-pending biometric identification system.

  • Led patent-pending cattle identification research using DINOv2 (92% accuracy)
  • Developed novel wavelet-based image enhancement pipeline
  • Built semantic document search engine with vector databases
  • Implemented LLM-based document Q&A systems using AWS Bedrock
Jun 2024 – Nov 2024 Techversant Infotech

Senior Software Engineer - AI/ML

Techversant Infotech

Developed and deployed AI/ML solutions for enterprise applications.

  • Built RAG applications with memory for contextual conversations
  • Developed face recognition systems with SOTA deep learning models
  • Designed AI-powered proctoring tools using YOLO
Sep 2023 – Jun 2024 Digital University Kerala

Senior Engineer - Data Science

Digital University Kerala

Led development of ML-based search infrastructure and data processing systems.

  • Engineered ETL pipelines for document extraction and Elasticsearch indexing
  • Led team of 3 in developing semantic search infrastructure
  • Created backend for 'Fun With AI' at Global Science Fest Kerala
Jun 2021 – Aug 2023 Digital University Kerala

Data Analyst

Digital University Kerala

Database optimization and analytics pipeline development.

  • Created automated data pipelines reducing processing time
  • Developed interactive data visualizations for reporting
Sep 2019 – Sep 2020 ICFOSS

Research Fellow

ICFOSS

NLP research for Malayalam language processing.

  • Developed Morphological Analyzer for Malayalam
  • Built sentiment analysis systems for Indian languages
  • Conducted research on YouTube comment data

Research

Patent-pending innovations in computer vision and biometrics

Patent Pending

Biometric Cattle Identification System

Computer vision system for individual cattle identification using muzzle patterns as biometric markers, analogous to human fingerprint recognition.

Problem

RFID-based livestock identification is susceptible to tampering, loss, and requires time-consuming manual verification.

Solution

Non-invasive, tamper-proof biometric identification using deep learning and novel image enhancement techniques.

PyTorch YOLOv11 DINOv2 PyWavelets OpenCV Pinecone

Technical Pipeline

1
Image Preprocessing - Resize, normalize, denoise
2
YOLOv11 Detection - Muzzle region cropping
3
Wavelet Enhancement - Novel ridge pattern extraction
4
DINOv2 Embeddings - 1024-dim feature extraction
5
Vector Search - Cosine similarity matching
92%
Accuracy
49ms
Inference
533ms
E2E Latency
420
Training Images

Key Innovation

Novel wavelet-based ridge enhancement algorithm adapting fingerprint recognition techniques (BayesShrink denoising, biorthogonal wavelet contrast enhancement, morphological skeletonization) for biological pattern extraction.

Research conducted at Digital University Kerala with literature review of 27 academic references. Dataset creation, model training, and end-to-end system architecture designed and implemented independently.

Industry Projects

Production-grade AI/ML solutions built at scale

Hybrid RAG Sales Intelligence

Proposal search assistant fusing vector search, graph database traversal, and Reciprocal Rank Fusion with 5-layer security.

  • 3-path query routing: metadata (Cypher) / content (semantic) / general
  • RRF ranking engine fusing 4 weighted sources (0.4/0.3/0.2/0.1)
  • Semantic chunking with cosine similarity thresholding at 0.5
Qdrant Neo4j LlamaGuard WebSocket Celery

Document Verification

AI-powered document verification using RAG and multi-agent orchestration for regulatory compliance.

  • Multi-agent architecture for extraction & verification
  • Hybrid RAG with confidence-based classification
  • 39 articles, 149+ compliance criteria verified
LangGraph ChromaDB GPT-4o FastAPI

Vision-Based Document Extraction

Multi-modal AI pipeline for structured data extraction from financial documents using Vision-Language Models.

  • Adapter pattern supporting 13+ document formats
  • VLM fallback strategy with quality thresholds
  • Multi-provider routing with priority-based failover
GPT-4 Vision Claude Vision Gemini FastAPI

AI-Powered Log Analytics Platform

Enterprise log analytics with multi-agent orchestration, semantic error grouping, and anomaly detection processing 10K+ daily logs.

  • 4-agent event-driven pipeline (Triage → Mapper → Analysis → Notifier)
  • Semantic error grouping with 0.85 similarity threshold and anomaly scoring
  • 5-workflow decision tree routing with 200ms–2000ms processing budgets
Multi-Agent Qdrant Redis Pub/Sub Langfuse Presidio

AI-Powered Outreach Automation

Agentic LLM platform orchestrating multi-phase target discovery, data enrichment, fitness scoring, and branded document generation via MCP server architecture.

  • 5-phase agentic workflow: discovery, enrichment, scoring, document generation, outreach
  • Custom MCP server with 11 tools for API abstraction and response trimming
  • Template-driven document pipeline (PPTX, DOCX, XLSX) with zero LLM hallucination in output
Claude AI MCP Protocol Pydantic python-pptx openpyxl

Agentic AI for Roadside Assistance

Conversational AI platform with real-time voice synthesis, sentiment analysis, and intelligent technician routing.

  • Multi-model LLM pipeline for real-time analysis
  • WebRTC-based live transcription with sub-256ms latency
  • Real-time sentiment tracking and escalation
ElevenLabs GPT-4o Claude WebSocket

AI-Powered Debt Collection

Voice AI platform with multi-model analysis pipeline for automated loan recovery conversations.

  • Sub-256ms voice synthesis latency
  • Automated promise extraction from calls
  • Stage-specific conversation strategies
ElevenLabs Silero VAD ONNX WebRTC

Production RAG System

Semantic search with two-stage retrieval, cross-encoder reranking, and content guardrails for specialized domains.

  • 94.7% query classification accuracy
  • 6 configurable chunking strategies
  • Bilingual support with real-time SSE streaming
Sentence-Transformers Qdrant Cross-Encoders FastAPI

Skills & Technologies

Tools and technologies I work with daily

Machine Learning & AI

Expert
PyTorch Transformers Scikit-learn ONNX Runtime LoRA/QLoRA vLLM

Large Language Models

Expert
GPT-4/4o Claude Gemini LangChain LangGraph MCP Protocol AWS Bedrock OpenRouter

Computer Vision

Expert
YOLO DINOv2 Vision Transformers OpenCV Wavelet Analysis OCR

NLP & RAG

Expert
RAG Systems Semantic Search Cross-Encoders Sentence-Transformers spaCy RRF Ranking

Databases & Search

Advanced
Qdrant Neo4j Pinecone ChromaDB Elasticsearch FAISS

AI Safety & Observability

Advanced
LlamaGuard Presidio Langfuse LLM Guardrails PII Detection

Backend & APIs

Advanced
FastAPI Pydantic Python AsyncIO WebSockets Celery PostgreSQL Redis

Voice & Conversational AI

Advanced
ElevenLabs WebRTC Silero VAD Real-time Streaming

Cloud & Infrastructure

Proficient
AWS Docker NVIDIA CUDA GPU Computing

Languages

Python
Expert
TypeScript
Advanced
JavaScript
Advanced
SQL
Advanced

Education & Credentials

Academic background and professional certifications

Education

Master of Science in Computer Science

Data Analytics

Indian Institute of Information Technology and Management - Kerala (IIITM-K)

Cochin University of Science and Technology

June 2017 - April 2020 First Class

Bachelor of Science

Computer Science, Statistics and Mathematics

Kristu Jayanti College, Bengaluru

June 2014 - March 2017

Certifications

Google Data Analytics Professional Certificate

Google

Building Real-Time Video AI Applications

NVIDIA Deep Learning Institute

Getting Started with Deep Learning

NVIDIA Deep Learning Institute

Languages

EN
English
Professional
ML
Malayalam
Native
SV
Swedish
Beginner

Get In Touch

Interested in collaborating on AI/ML research or projects? I'm always open to discussing new opportunities.

Send a Message

Email
arnolps172@gmail.com
Phone
+91 9048357172
Location
Kannur, Kerala, India
Connect
Social Links