Madhumitha Kolkar
Vetted Talent
Madhumitha Kolkar
Vetted Talent
Seasoned Machine Learning Engineer with 3.3 years of professional experience working with a specialization in Natural Language Processing, Computer Vision, Deep Learning and Generate AI.
- Role
Machine Learning Engineer
- Years of Experience
4 years
- Professional Portfolio
View here
Skillsets
- Algorithms
- Data Structures
- Debugging
- Machine learning techniques
- Model deployment
- programming languages
- System Design
- Cloud & ml ops
- Python - 5 Years
- JS - 3 Years
- MLOps - 4 Years
- Microservices - 3 Years
- SQL - 4 Years
- DevOps - 2 Years
- Generative AI - 3 Years
Vetted For
10Skills
- Roles & Skills
- Results
- Details
Machine Learning Scientist II (Places) - RemoteAI Screening- 82%
- Skills assessed :Large POI Database, Text Embeddings Generation, ETL pipeline, LLM, Machine Learning Model, NLP, Problem Solving Attitude, Python, R, SQL
- Score: 74/90
Professional Summary
4Years
- Jan, 2024 - Present1 yr 3 months
Machine Learning Engineer
SNOWKAP | POWERWEAVE - Jan, 2021 - Jan, 20243 yr
Machine Learning Engineer
MERCEDES BENZ RESEARCH AND DEVELOPMENT - Jan, 2020 - Jan, 20211 yr
Data Scientist
DELOITTE
Applications & Tools Known
OpenCV
NumPy
Dialogflow
Mediapipe
Streamlit
Pandas
PyTorch
scikit-learn
Android SDK
MySQL
MongoDB
Git
.png)
Flask
.png)
FastAPI
PostgreSQL
FAISS
Pinecone
AWS Lambda
AWS S3
AWS EC2
.png)
Docker
.jpg)
Hugging Face
Airflow
AWS
Work History
4Years
Machine Learning Engineer
SNOWKAP | POWERWEAVEJan, 2024 - Present1 yr 3 months
Speech Emotion Detection for Agentic Chatbots: Orchestrated an end-to-end classifier from scratch, achieving 0.86 F1-score using Conv1D / BiLSTM / GRU on TESS, RAVDESS, CREMA-D, and Surrey AV datasets. Spearheaded data preprocessing and augmentation strategies, leveraging spectral analysis and pitch shifting to expand datasets by 300%. Engineered and deployed a high-performance vector search system on AWS utilizing dense OpenAI LLM embeddings. Optimized Stable Diffusion for automated product background integration. Streamlined LlamaParse integration into the RAG based ESG analysis workflow. Applied prompt engineering techniques to build 3 custom GPTs.
Machine Learning Engineer
MERCEDES BENZ RESEARCH AND DEVELOPMENTJan, 2021 - Jan, 20243 yr
Pioneered Conversational AI for Service Assistance: Created a Seq2Seq LSTM chatbot for intent classification and response generation, achieving an accuracy of 93%. Enhanced Predictive Maintenance (HVAC & Battery Systems) by applying XGBoost & Random Forest. Led development of a YOLOv5 powered image classification system. Led Mercedes-Benz Infotainment Data Parsing: Devised a custom Python parser, boosting UDC processing efficiency by 80%. Advanced Research Initiatives including fine-tuning BERT on custom data.
Data Scientist
DELOITTEJan, 2020 - Jan, 20211 yr
Enhanced legal transcription accuracy by 20% by fine-tuning DeepSpeech ASR. Formulated Transcript Clarity with Speaker Diarization: Introduced speaker diarization as a potential solution to differentiate between speakers.
Achievements
- • Exemplary Performance: Recognized as a "Star Performer" for consistently exceeding established company benchmarks by 40%. • Mentorship and Talent Acquisition: Successfully trained and mentored over 15 individuals, and Actively participated in hiring for senior positions (T7/T8/T9s) and fresher, contributing to attracting top talent for company growth. • Open-Source Advocate: Made 4 notable contributions to popular Machine Learning libraries like Keras, TensorFlow, and OpenAI Whisper, actively promoting collaborative development within the Machine Learning community. - Speaker for Google , Conscious Algorithms : A Talk on AI Safety.
- Star Performer award
- Google Dev Conference speaker
- Mentorship of 15+ individuals
- Presented expertise at Google Dev Conference
Major Projects
11Projects
QuantumAR
Developed an Augmented Reality application with OpenCV and Python for real-time feature matching and dynamic object replacement.
Noah
Designed a smart chat/recommendation bot using FastAPI, Python, Dialogflow, MySQL, and NLP for a custom shopping site.
AirFlow
Developed an interactive gesture-based Air Canvas using ML, Mediapipe, and OpenCV for tracking hand movements and recognizing gestures.
paperScribe
Architected and implemented PaperScribe, a Retrieval-Augmented Generation (RAG) AI system powered by GPT-3.
Moodmap
Engineered a novel Multimodal AI system for real-time emotion analysis.
SigSafe
Implemented a Siamese network architecture for signature verification.
SayWhatNow
Developed a deep learning-based custom next-word predictor utilizing LSTMs.
Notii-fy
Feb, 2024 - Mar, 2024 1 month
Engineered Notiify, an ad-free, local music player application inspired by Spotify. Utilizing Python and speech recognition, enabling hands-free music control by allowing users to voice-activate song playback. Attained an average voice command response time of 0.88 seconds.
OpinionSense
Jan, 2024 - Feb, 2024 1 month
Coded and implemented OpinionSense, a sentiment analysis system for reviews using a Recurrent Neural Network (RNN) from scratch. Achieved an F1-score of 0.85.
Cropcure_AI
Jan, 2024 - Feb, 2024 1 month
Created CropCure AI, a Flask application leveraging Deep Learning for real-time Blythe disease detection in potato leaves. Gained an F1-score of 88%
MK_LLM
Jan, 2024 - Feb, 2024 1 month
- Devised a bigram character-based architecture, achieving a competitive F1-score of 87.2 on a held-out validation set.
- Trained MK-LLM on a subset of OpenWebText, a massive text dataset comparable to GPT-2 training data.
Education
Bachelor Of Engineering - Computer Science
SDMCET Dharwad (2020)
Certifications
Machine Learning
DeepLearning.AI- Stanford (Apr, 2024)