Aravind Sasi nair purayath - AI – Data Specialist

Recommended expert

Hamburg, Germany

Experience

Aug 2024 - Present

1 year 6 months

AI – Data Specialist

Emirates Islamic Bank

Architected and deployed LLM based AI agents, RAG pipelines, and vector search solutions for decision support across retail banking department.
Developed and shipped robust AI pipelines with guardrails, error handling, monitoring, and fallback logic ensuring high reliability outcomes and compliance with data privacy.
Developed and deployed ML models to identify transactional anomalies, improving fraud detection and risk assessment in high-volume datasets for credit risk modelling.
Built, evaluated and fine-tuned ML models to generate propensity scores for customers used to drive personalized targeting campaigns for credit cards and personal finance/loan products.
Developed an NLP pipeline using BERT embeddings and spaCy NER for SMS/email analysis and customer query logs.
Trained machine learning models using Isolation Forest to classify user behaviour and detect anomalies.
Extracted, cleaned, enriched and feature engineered datasets from different sources to build feature stores that powered ML model training.
Led development of dashboards using Power BI, Grafana, and Prometheus to monitor model performances, KPI trends, and marketing metrics.
Built multi-touch attribution models using logistic regression and time-decay weights to evaluate lead quality.
Developed scalable ETL pipelines from CRM, T24, SAP, and ERP, supporting millions of monthly transactions.
Integrated testing and CI/CD workflows for robust data pipeline deployment.

Aug 2022 - Aug 2024

2 years 1 month

Senior Data Specialist (AI/ML)

Flipkart

Built and deployed reinforcement learning ad personalization system (K-Means clustering, XGBoost, collaborative filtering) using Azure ML; monitored via A/B tests achieving measurable engagement uplift.
Trained XGBoost model via Azure ML for geo-targeted campaigns; integrated with marketing platforms and monitored performance against campaign KPIs.
Deployed BERT-based classifier via Azure Functions, orchestrated bi-weekly retraining on Databricks, integrated with Elasticsearch for product catalog updates.
Extracted, cleaned, and visualized data from multiple sources to curate high-quality datasets for machine learning models, and evaluated, fine-tuned, and deployed those models using Azure or internal hosting solutions.
Translated marketing/product team requirements into ML solutions; communicated complex model behavior in business terms to non-technical stakeholders.
Analyzed 50M+ row datasets using PySpark and SQL for near real-time decision support; built scalable data pipelines supporting analytics and ML feature stores.
Improved push notification CTR by 11% by analyzing heatmap data (views, clicks, hovers) and optimizing key landing pages.

Feb 2022 - Aug 2022

7 months

Analyst

Muvin

Mentored developers and employees on ML and automation technologies, creating high-value POCs and MVPs.
Designed and deployed a custom ML model for feedback text analysis, integrated as a reusable AI component across projects.
Developed, implemented, and optimized ETL data pipelines to efficiently process and integrate large-scale datasets from diverse sources into centralized platforms.
Deployed Grafana and Prometheus for real-time monitoring of Azure infrastructure, enhancing system reliability and performance tracking.

Mar 2021 - Sep 2021

7 months

Data Science Intern

Flip Robo

Designed and implemented A/B experiments to optimize customer retention and loan offerings for a banking client.
Implemented lifecycle automation using Azure ML pipelines for retraining a loan default classifier every two weeks, with triggers based on data drift monitored via MLflow.
Worked on real-time fraud detection models on scalable ML infrastructure using containerized workflows via Kubernetes and CI/CD pipelines on AWS SageMaker.
Developed continuous data drift monitoring using MLflow and SageMaker model monitor to ensure prediction reliability in production.

Jul 2019 - Mar 2021

1 year 9 months

Data Analyst

Swiggy (Bundl Technologies)

Used a Thompson sampling multi-armed bandit approach in production (Python + Flask API) to dynamically serve push notifications across user segments; achieved a 7% CTR uplift over static rules.
Utilized association rule mining on transactional data to identify frequently co-ordered item combinations and informed bundling and cross-selling strategies.
Scraped competitor pricing daily using Selenium and analyzed price elasticity using regression models in pandas/statsmodels; fed into the internal pricing recommendation dashboard in Power BI.
Used uplift modeling and counterfactual inference techniques to isolate the true effect of personalized promotions and targeted campaigns.
Worked on multiple machine learning POCs related to product pricing elasticity and customer segmentation.
Built demand forecasting models to predict order volumes and optimize supply chain logistics.

Jul 2018 - Jul 2019

1 year 1 month

Consultant - Freelance

Vrindavan Consultants

Enabled the team to adopt data-driven scheduling and inventory planning, improving resource utilization by 15%.
Conducted competitor analysis and provided data-backed recommendations for local SEO and marketing spend allocation.
Created a pricing optimization model using Excel and Python to recommend tiered service bundles based on seasonal demand.
Built a Power BI dashboard to track inquiries, service requests, and customer lifetime value across regions.
Improved lead conversion by analyzing customer acquisition data and service patterns.

Jul 2017 - Jul 2018

1 year 1 month

Associate Financial Reporter

Digital Nirvana

Attained solid understanding of financial markets and exchanges; worked with finance teams to assist with quarterly and yearly financial press releases.
Partnered with executives to analyze workflow data, identifying bottlenecks and reducing ETAs; ensured data quality and consistency by implementing monitoring processes and best practices.
Supported data analysis for troubleshooting and report generation using Power BI and SQL for daily and quarterly earnings reports for multiple clients.
Automated quarterly earnings report generation using SQL queries and Power BI dashboards for 10+ clients, significantly reducing manual effort and standardizing reporting templates.

Summary

AI & Data Specialist with 7+ years of experience designing and delivering innovative AI-driven solutions and data products across industries. Skilled in managing end-to-end AI/ML modeling, building automation pipelines, and deploying scalable, real-time AI systems. Expertise in Generative AI, LLMs, and Agentic AI, with a focus on collaborating with cross-functional teams to integrate advanced technologies while ensuring scalability, reliability, and compliance.

Skills

Ai/ml Algorithms

Transformers
Diffusion Models
Gradient Boosting Machines (E.g., Xgboost, Lightgbm, Catboost)
Random Forests
Support Vector Machines (Svm)
Convolutional Neural Networks (Cnns)
Recurrent Neural Networks (Rnns) And Lstms
Graph Neural Networks (Gnns)
Deep Q-networks (Dqn)
Clustering (E.g., K-means, Dbscan)
Statsforecast

Business Tools

Microsoft Dynamics Crm
Erp
Power Bi
Azure Devops

Tools And Frameworks

Pytorch
Tensorflow / Keras
Scikit-learn
Hugging Face Transformers
Pandas
Numpy
Dask
Apache Spark (Pyspark)
Sql
Snowflake
Bigquery
Redshift
Databricks
Docker
Kubernetes (Aks)
Aws Sagemaker
Google Vertex Ai
Azure Ml
Git
Github
Power Bi
Streamlit
Qliksense
Copilot Studio
Claude

Coding Languages

Python
Javascript
Sql (Postgresql, Sql Server)
C++

Azure

Ai Foundry
Cognitive Services
Azure Function App
Azure Speech Studio
Azure Devops
Azure Key Vault
Azure Openai
Azure Data Factory (Adf)
Form Recognizer
Logic Apps
Rag

Agentic Ai Frameworks

Mcp (Model Context Protocol)
Langgraph
Pydantic
Haystack
Semantic Kernel
Autogen
Crewai
Aws Bedrock Agent Builder
Evaluation & Guardrails
Model Monitoring

Languages

English

Advanced

German

Elementary

Education

Aug 2013 - May 2017

CMS College of Engineering and Technology

Bachelors in Engineering, Electronics and Communication · Electronics and Communication · Coimbatore, India

Need a freelancer? Find your match in seconds.

Try FRATCH GPT

Similar Freelancers

Discover other experts with similar qualifications and experience

Experience

AI – Data Specialist

Emirates Islamic Bank

Senior Data Specialist (AI/ML)

Flipkart

Analyst

Muvin

Data Science Intern

Flip Robo

Data Analyst

Swiggy (Bundl Technologies)

Consultant - Freelance

Vrindavan Consultants

Associate Financial Reporter

Digital Nirvana

Summary

Skills

Languages

Education

CMS College of Engineering and Technology

Bachelors in Engineering, Electronics and Communication · Electronics and Communication · Coimbatore, India

Similar Freelancers

Senior Data Scientist

Data Scientist

Data Scientist

Data Scientist & Data Engineer

Solution Engineer (Data & ML Integration)

AI Product Manager and Engineer

AI Consultant & Advisor

Test Manager and Software and Hardware Tester

Data Scientist

AI Strategy Consultant

Agentic AI for a DeepResearch project

Head of Risk Modeling & Cloud Infrastructure

NLP/LLM Chatbot

Document parser for picking lists (PDF & PNG)

Data-Scientist/AI Engineer

Technical PMO | Delivery Master | LLM-Expert

Principal (Data Scientist/Data Engineer/Gen AI Engineer)

Senior Analytics Engineer

Consultant for data-driven AI solutions

Partner

AI-Backend Developer Intern

NLP Engineer

Cloud-Architect, Senior Solution Architect, Senior Software-Engineer

Senior AI Architect & Engineer

Interim Business Analyst / Product Owner

Workshop Leader 'Introduction to AI Development Tools'

AI Engineer

Senior Data Scientist

Development of an AI-driven social media automation for topic identification, text generation, and publishing

ESG Data Analyst (Volunteer, part-time)