AI Enthusiast. Engineer. MBA Finance
π¬Data is how we listen to reality, but data science is how we translate what we hear into something we can understandπ‘
π Get in touch with me π π
πGitHub | βοΈakash.mathur2289@gmail.com |
βοΈMedium | π’LinkedIn |
#οΈβ£Kaggle | π€Space |
π οΈGenerative AI Applications π¨π½βπ»
Senior Data Scientist β Automotive Supply Chain Technology & Aftermarket (Jun 2021 β Present)
$500k+
in revenue by architecting end-to-end product on AWS
that forecast Vehicles Scrappage
. Setup Feature store and model monitoring
with SageMaker
to track and analyze metrics.deployment
and serving
with FastAPI through an efficient CI/CD
integrated serverless workflow using AWS, Docker, Terraform and GitHub.80%
by architecting end-to-end application on AWS. It recommends top news articles through similarity
search and summaries generated from a fine-tuned
FLAN-T5 model.sentiment
analysis using a fine-tuned
RoBERTa model and identifying prevalent issues using topic modelling
via BERTopic on AWS.RAG
system utilizing Hybrid Search
and Reranking
techniques using open source LLMs, while implementing fine-tuning strategies to optimize both ingestion
and inferencing
for enhanced performance.Assistant Manager - Quantitative Modelling (Nov 2018 β Jun 2021)
90%
by designing ETL
pipelines tailored for large-scale data and leveraging ARIMA
for revenue forecasting using Databricks
.Client Finance Analytics - Global Markets Technology (May 2015 β Nov 2018)
ETL
pipelines, enabling precise identification of high-risk hedge fund investors with the Random Forest classifier.Dimensionality Reduction
and Clustering
Techniques to identify distinct client groups, leading to deeper customer understanding.Large Language Model (LLM)
, including conversational AI chatbot
, semantic search
and text summarization
, coupled with UI creation using LangChain
and LlamaIndex
.RAG
applications, optimizing both ingestion (chunking, metadata, multi-indexing
) and inferencing (query transformations, advanced retrieval strategies, re-ranking
) stages for enhanced performance. 1. Conversational AI (Chatbot π€) with RAG using LangChainπ¦οΈ & LlamaIndexπ¦
Llama2
ChatBot using LlamaIndex and Streamlit [Medium, GitHub]Mistral-7B-Instruct
Based Multi-PDFs ChatBot using LangChain and Streamlit [GitHub]Llama2-7B
Based CSV ChatBot using LangChain [GitHub]Bedrock
[GitHub] 2. Advanced RAGππ
Context
& MetaData
using LlamaIndex [Medium, GitHub]Reranker
Models using LlamaIndex [Medium, GitHub]Augmentation
for Next-Level Search
using LlamaIndex [Medium, GitHub] Tracking
and Debugging
of Document Changes using LlamaIndex [Medium, GitHub] 3. LLM Fine Tuning π§ and Applications π‘
Mistral-7Bβs
Performance through Finetuning using QLoRA [Medium, GitHub]T5
Fine Tuning & Evaluation for Text Summarization [GitHub]Falcon-7B
Based Video π¬ Summarization using Langchain [GitHub]Audio
GenerationπΉ using Audio Craft [GitHub] 4. Model Serving and Deployment βοΈ
FAISS
with AWS Serverless Architecture [Medium, GitHub]5. AWS Serverless Architectures for Big Data Workloadsπ
Batch
Jobs Execution [Medium, GitHub]Lambda
Invocation [Medium, GitHub]Step Functions
[Medium, GitHub]π Technologies | π Interests |
---|---|
β’ Languages: Python, SQL, Spark β’ Machine Learning: Scikit-Learn, PyTorch, LangChain, LlamaIndex, Faiss, NumPy, Pandas, MLflow, TensorFlow, NLTK, spaCy, OpenCV β’ Cloud: AWS (SageMaker, Lambda, Batch, Step Functions, ECS, ECR, API Gateway, S3), Azure (Machine Learning, Data Factory, Databricks), β’ MLOps: BentoML, MLflow, DVC, Docker, Terraform, CI/CD, Git, GitHub Actions β’ Visualization: Tableau, Power BI β’ Database: MySQL, SQLite |
β’ Generative AI β’ NLP β’ Recommendation Systems β’ MLOps β’ Stock Market Analysis, Macroeconomics β’ Swimming, Yoga, Meditation, Cooking |
Post Graduate Diploma in Management - Financial Services | K J Somaiya Institute of Management, Mumbai, India | 2013-2015 |
Bachelor of Technology - Electronics & Communication | Rajasthan Technical University, India | 2008-2012 |