Available for opportunities

Pallavi
Bembade Data Scientist · AI/ML Engineer · Generative AI Specialist

3+ years building production-grade AI systems — from RAG chatbots and NLP pipelines to Agentic AI — across Healthcare, Automotive, and IP domains. Pune, India.

3+
Years Experience
5
AI Projects Shipped
9.21
CGPA / 10.0
3
Certifications
Who I am

About Me

I'm a Data Scientist and AI/ML Engineer with 3+ years of experience specializing in LLMs, Retrieval-Augmented Generation (RAG), and Agentic AI systems.

At CognoPI Solutions, I build end-to-end AI solutions for clients across Healthcare, Automotive, and Intellectual Property domains — taking projects from raw data ingestion to deployed, production-grade REST APIs.

I'm passionate about turning complex AI research into measurable business impact — whether that's reducing a 2-week patent search to milliseconds, or enabling 50+ corporate clients to self-serve health queries 24/7.

📍
Location
Pune, India
🎓
Education
B.E. Electronics & Telecommunication
MGM's College of Engineering, Nanded · CGPA 9.21
🌐
Languages
English (Professional) · Hindi · Marathi
☁️
Cloud Platforms
AWS · Azure

Technical Skills

⌨ Programming & Data
PythonSQLPandas NumPyData WranglingEDA Statistical Analysis
🤖 ML & Deep Learning
Machine LearningDeep Learning Feature EngineeringXGBoost PyTorchScikit-learnSHAP
🔤 NLP & Transformers
HuggingFaceSentence-Transformers SpaCyNLTKTF-IDF Word2VecTokenization
✨ Generative AI & LLMs
LangChainLangGraphRAG Agentic AIOpenAIAzure OpenAI AWS BedrockPineconeFAISS Prompt Engineering
⚙ MLOps & Deployment
FastAPIFlaskStreamlit DockerCI/CDGitHub Actions AWS EC2/ECR/S3Azure
🗄 Databases
PostgreSQLMySQL PineconeCosmos DB Vector DBAWS S3
Where I've worked

Experience

Feb 2024 – Present
Current
Data Scientist
CognoPI Solutions Pvt. Ltd. · Pune, India
  • Designed and deployed end-to-end AI/ML and NLP solutions for clients across healthcare, automotive, and IP intelligence domains.
  • Built production-grade systems using Python, HuggingFace, FastAPI, LangChain, and AWS — from raw data ingestion through to deployed REST APIs and CI/CD pipelines.
  • Researched and evaluated emerging LLM frameworks and vector database technologies to implement best-fit solutions per client use case.
Feb 2021 – Oct 2021
QA Engineer
O/E/N India Ltd. · Pune, India
  • Developed and executed structured test plans ensuring quality across functional and regression testing cycles.
  • Identified recurring defect patterns and recommended preventive measures to reduce post-release issues.

Featured Projects

01
MedeX AI
Medical RAG Chatbot

Built a medical RAG chatbot enabling clinic staff to query 100+ treatment guidelines (WHO, NIH, CDC, AIIMS) using PubMedBERT embeddings + Pinecone vector DB. GPT-4o-mini grounded responses to prevent hallucinations. Full CI/CD via GitHub Actions → Docker → AWS ECR → EC2.

Business Impact Reduced manual document search from minutes to seconds. Enabled 50+ corporate clients to self-serve health policy queries 24/7.
LangChainOpenAIPinecone PubMedBERTFlaskDocker AWS EC2/ECRGitHub Actions
02
AutoSense AI
Vehicle Service Intelligence Platform

End-to-end vehicle service intelligence platform ingesting 4 data sources (141K+ events) into a 120-feature dataset. Trained XGBoost models (F1=0.82, ROC-AUC=0.89) with SHAP explainability. Multilingual RAG chatbot in English, Hindi & Marathi.

Business Impact 23% improvement in service follow-up conversion at 5-dealer pilot. Proactive high-risk vehicle identification 30 days before service due.
XGBoostSHAPSMOTE Azure OpenAIStreamlitPlotlyReportLab
03
PatentIQ NLP
Patent Similarity & NLP Classification

Automated patent prior art search and CPC multilabel classification across 1M patent records (USPTO + EPO). Built a 7-step NLP preprocessing pipeline, PatentSBERTa embeddings, 4 similarity metrics, and an interactive Pyvis force-directed network graph.

Business Impact Prior art search reduced from 2 weeks to milliseconds. 89-90% CPC classification accuracy. Eliminated R&D duplication.
PatentSBERTaHuggingFaceFastAPI PyTorchPyvisPostgreSQL AWS S3/EC2
Credentials

Certifications

☁️
Microsoft Azure Fundamentals
AZ-900 · Microsoft Azure
🟠
AWS Cloud Practitioner
Amazon Web Services
🧠
Machine Learning Specialization
Coursera · deeplearning.ai

Let's Collaborate

Open to new opportunities, freelance projects, and interesting AI/ML collaborations. Feel free to reach out!