HomeSkillsExperienceWorkContact
Available · Industrial PhD & AI Roles · Germany

SANKARDEV S

|

AI/ML Engineer with 3+ years building production ML systems. Published researcher with 95.08% F1-score NLP model (JDSIS 2026). Specialising in LLMs, NLP pipelines, and multimodal AI — targeting AI roles and industrial PhD opportunities in Germany.

Published Researcher · JDSIS 2026
AI
Emotion Recognition F195%
Vocal Anomaly Accuracy78%
Training Latency Saved30%

model = RoBERTa.from_pretrained(

"emotion-classifier"

)

result = model.predict(text)

▶ F1-Score: 95.08% · Classes: 28

🎓 Research Interests · Industrial PhD

Multimodal AILLM AlignmentNLP
GEN AILangChainMLOpsFastAPI
Scroll

Research Metrics

0.00%

F1-Score

RoBERTa NLP · JDSIS 2026

0K+

Text Samples

GoEmotions + Hate Speech pipeline

0%

Latency Reduced

ML training optimisation

0.0%

CREMA-D Accuracy

Multimodal Wav2Vec2.0 model

0

Emotion Classes

EmoTract real-time classifier

Technical Stack

Built for AI at Scale

AI & Machine Learning15 skills
🔥PyTorch
🧠TensorFlow
🤗Hugging Face
📖BERT
🔬RoBERTa
🎙️Wav2Vec2.0
⛓️LangChain
📡RAG
PySpark
🎯Multimodal AI
✍️Prompt Engineering
📊Classical ML
🔀LLM Data Pipelines
💬Sentiment Analysis
🖼️Deep Learning (CNN)
🔥PyTorch
🧠TensorFlow
🤗Hugging Face
📖BERT
🔬RoBERTa
🎙️Wav2Vec2.0
⛓️LangChain
📡RAG
PySpark
🎯Multimodal AI
✍️Prompt Engineering
📊Classical ML
🔀LLM Data Pipelines
💬Sentiment Analysis
🖼️Deep Learning (CNN)
MLOps & Deployment8 skills
🚀FastAPI
🐳Docker
☁️AWS EC2
♾️CI/CD
🗂️Git
🔌REST APIs
🔄WebSockets
🔵Socket.IO
🚀FastAPI
🐳Docker
☁️AWS EC2
♾️CI/CD
🗂️Git
🔌REST APIs
🔄WebSockets
🔵Socket.IO
Web & Backend14 skills
🐍Python
🚀FastAPI
💙TypeScript
🌐JavaScript
⚛️React
Next.js
🟢Node.js
🎸Django
🧪Flask
🐘PHP
🔴Laravel
🗄️SQL
🍃MongoDB
🟥Redis
🐍Python
🚀FastAPI
💙TypeScript
🌐JavaScript
⚛️React
Next.js
🟢Node.js
🎸Django
🧪Flask
🐘PHP
🔴Laravel
🗄️SQL
🍃MongoDB
🟥Redis
Professional6 skills
🔭ML Research
📝Published Author
🎯Technical Leadership
🏭Production ML Deployment
🔍Code Reviews
🏎️Performance Optimisation
🔭ML Research
📝Published Author
🎯Technical Leadership
🏭Production ML Deployment
🔍Code Reviews
🏎️Performance Optimisation

The Journey

Professional milestones and academic achievements.

Research Assistant

University of East London
September 2024 – Present
London, United Kingdom
  • Built a data pipeline processing 250,000+ text samples from GoEmotions and Hate Speech corpora.
  • Fine-tuned RoBERTa for multi-class emotion recognition; achieved 95.08% F1-score, published in JDSIS (2026).
  • Reduced model training latency by 30% through batching optimisations across classical and transformer-based models.
  • Developed SoundSense, a multimodal vocal anomaly detection system using Wav2Vec2.0.
  • Achieved 78.10% accuracy on CREMA-D, outperforming SVM/RF baselines by 30%.

Software Engineer

Techise Solutions
February 2023 – October 2023
Alappuzha, Kerala, India
  • Built backend systems using Laravel and MySQL for multiple concurrent client projects.
  • Delivered React.js frontends with full mobile responsiveness across all deliverables.

Software Associate

Riss Technologies
May 2022 – May 2023
Ernakulam, Kerala, India
  • Delivered 200+ bespoke software solutions across Python, PHP, and React; 95% client satisfaction.
  • Deployed predictive ML models into production, reducing manual data processing time by ~20%.

Education

M.Sc. Artificial Intelligence (with Industrial Placement)

2023 – 2025

University of East London, UK

Distinction (70%) — approx. 1.0–1.3 on German grading scale

B.Sc. Computer Applications

2019 – 2022

Kerala University, India

Selected Projects

Things I've Built

Full archive
01

VoxChain – Real-Time LLM Voice Agent

Real-time voice AI system with bidirectional streaming (speech ↔ LLM ↔ audio). Deployed end-to-end agentic LLM pipeline with low-latency audio I/O.

LangChainQwen LLMFastAPIWebSockets
02

SmartSafe – Multimodal Liveness Detection

Attendance system using facial recognition combined with audio liveness scoring for anti-spoofing. Generates a fraud-resistance confidence score from vision and audio signals.

PythonOpenCVFace RecognitionAudio Processing
03

SoundSense – Multimodal Emotion Detection

Cross-modal system detecting emotional inconsistencies between speech text and vocal tone. Achieved 78.10% accuracy, outperforming SVM/RF baselines by 30%.

Wav2Vec2.0RoBERTaPyTorchCREMA-D
04

EmoTract – 28-Class Real-Time Emotion Classifier

Multi-label platform classifying 28 emotion categories from text input in real time. Full-stack deployment from fine-tuned transformer model to containerised web interface.

BERTRoBERTaDjangoReactTypeScriptDocker
📄

Latest Publication

"NLP-Framework for Youngsters with Advanced Transformer-Based Models"

Journal of Data Science and Intelligent Systems (JDSIS), 2026

95.08% F1-ScoreRoBERTa · BERT28 Emotion Classes
Read Paper

Let's Connect

I'm currently open to new opportunities in AI Research and Full-Stack Engineering. Whether you have a question or just want to say hi, I'll try my best to get back to you!

s4nkar.connect@gmail.com
Germany
+44 7460054747

© 2026 Sankar Dev S. All rights reserved.