I’m a Generative AI/ML Engineer with 3+ years of experience building production-scale LLM, RAG, agentic AI, and Voice AI systems. In my current role at Sterlite Technologies (STL), I architected and shipped an agentic multi-agent IVR/call-routing platform that serves 1,000+ daily interactions per multi-tenant setup, delivering a 90%+ reduction in IVR latency while improving GPU memory efficiency by ~60%. I also built multilingual RAG pipelines to support 10+ low-resource Indian languages and reduce unanswered queries, using automated document ingestion and smart retrieval matching. Alongside LLM systems, I’ve led the end-to-end delivery of a multilingual ASR–TTS web platform, including post-call transcript generation, speaker diarization, call summarization, and sentiment analysis for contact-center workflows. I enjoy turning complex ML and data-quality problems into reliable production solutions, mentoring a small team, and helping others by advising on diagnostics and model feedback loops—always aiming for systems that are accurate, efficient, and scalable.…

POOJA BHAVSAR

I’m a Generative AI/ML Engineer with 3+ years of experience building production-scale LLM, RAG, agentic AI, and Voice AI systems. In my current role at Sterlite Technologies (STL), I architected and shipped an agentic multi-agent IVR/call-routing platform that serves 1,000+ daily interactions per multi-tenant setup, delivering a 90%+ reduction in IVR latency while improving GPU memory efficiency by ~60%. I also built multilingual RAG pipelines to support 10+ low-resource Indian languages and reduce unanswered queries, using automated document ingestion and smart retrieval matching. Alongside LLM systems, I’ve led the end-to-end delivery of a multilingual ASR–TTS web platform, including post-call transcript generation, speaker diarization, call summarization, and sentiment analysis for contact-center workflows. I enjoy turning complex ML and data-quality problems into reliable production solutions, mentoring a small team, and helping others by advising on diagnostics and model feedback loops—always aiming for systems that are accurate, efficient, and scalable.…

Available to hire

I’m a Generative AI/ML Engineer with 3+ years of experience building production-scale LLM, RAG, agentic AI, and Voice AI systems. In my current role at Sterlite Technologies (STL), I architected and shipped an agentic multi-agent IVR/call-routing platform that serves 1,000+ daily interactions per multi-tenant setup, delivering a 90%+ reduction in IVR latency while improving GPU memory efficiency by ~60%. I also built multilingual RAG pipelines to support 10+ low-resource Indian languages and reduce unanswered queries, using automated document ingestion and smart retrieval matching.

Alongside LLM systems, I’ve led the end-to-end delivery of a multilingual ASR–TTS web platform, including post-call transcript generation, speaker diarization, call summarization, and sentiment analysis for contact-center workflows. I enjoy turning complex ML and data-quality problems into reliable production solutions, mentoring a small team, and helping others by advising on diagnostics and model feedback loops—always aiming for systems that are accurate, efficient, and scalable.

See more

Language

English
Fluent
Hindi
Fluent
Gujarati
Fluent

Work Experience

AI Developer — Generative AI & LLM Systems at Sterlite Technologies (STL)
December 1, 2023 - June 30, 2026
Architected and implemented a multi-tenant agentic multi-agent IVR system (Asterisk, MCP orchestration, RTP gateway, LangChain/LangGraph, STT/TTS) to eliminate manual call routing. Achieved 90%+ IVR latency reduction and reduced peak GPU memory by ~60% using an MoE-inspired routing approach with prompt-engineered intent routing on a 4-bit NF4 quantized Llama-3.2-3B backbone. Built a scalable multilingual RAG pipeline supporting 1,000+ daily tenant interactions with per-tenant vector stores and automated ingestion of PDF/DOCX/PPTX/CSV. Reduced unanswered queries across 10+ low-resource Indian languages using IndicTrans2 translation, MMR retrieval, and RapidFuzz-based FAQ matching, while reducing peak GPU memory by ~60%. Extended a multilingual ASR-TTS full-stack web platform with transcript generation, speaker diarization, call summarization, and sentiment analysis, using QLoRA fine-tuning and integration across the agentic pipeline.
AI Developer – Generative AI & LLM Systems at Sterlite Technologies (STL)
December 1, 2023 - Present
Architected a production Agentic AI IVR system (Asterisk, MCP Server, RTP gateway, LangChain/LangGraph orchestration, Chainlit UI, STT/TTS), cutting call-handling latency from multi-second to sub-100ms and enabling multi-tenant scalability. Built a multi-tenant ConversationalRetrievalChain RAG pipeline (LangChain, ChromaDB, Ollama embeddings) with per-tenant vector stores and MMR retrieval (k=10, fetch_k=50), serving 1,000+ daily Q&A interactions with sentiment analysis on post-call transcripts. Deployed quantized Llama-3.2-3B-Instruct (4-bit NF4, 8-bit fallback) with async inference and CPU fallback, reducing peak memory by ~60%. Delivered bilingual English/Hindi AI assistant with IndicTrans2 for real-time translation and template matching via RapidFuzz.
AI Engineer (RAG-based Q&A System) at Sterlite Technologies
December 1, 2023 - Present
Built a RAG-based Q&A system enabling accurate information retrieval from structured and unstructured data. Developed IVR flows with Asterisk, speech-to-text, and AI-powered responses using LLMs; created a transcription module for dial centers and multi-tenant chatbots/voice bots; enhanced user interaction and summarization.
AI/ML Trainer at Grass Solutions Pvt Ltd
November 1, 2023 - December 31, 2023
Delivered full-time hands-on training in Python, Machine Learning, Deep Learning, and DevOps fundamentals to trainees, building practical proficiency aligned with upcoming industry roles.
AI/ML Intern — Cybersecurity at ISRO – Space Applications Centre
January 1, 2023 - June 30, 2023
Built a DGA detection model by extracting n-gram and entropy features from 1M+ domain samples and training a character-embedding LSTM (TensorFlow/Keras), achieving 98.4% accuracy and 0.988 ROC-AUC on 200K+ evaluation samples. Implemented a real-time inference pipeline by streaming 50,000+ Zeek DNS log entries via Kafka into a Dockerized FastAPI endpoint, improving threat detection by 40% and reducing manual log-review effort by 60%.
AI/ML Intern — Cybersecurity at ISRO – Space Applications Centre (SAC)
January 1, 2023 - June 30, 2023
Developed a character-embedding LSTM for DGA detection using 1M+ domain samples; achieved 98.4% accuracy and 0.988 ROC-AUC on 200K+ evaluation samples. Built a real-time pipeline to stream 50,000+ Zeek DNS log entries via Kafka (producer/consumer) into a Dockerized FastAPI inference endpoint, improving threat detection by 40% and reducing manual log review effort by 60%.
Machine Learning Intern – Cybersecurity at ISRO – Space Applications Centre
January 1, 2023 - June 1, 2023
Built an end-to-end DGA detection system: extracted n-gram/entropy features from 1M+ domain samples, trained a character-embedding LSTM achieving 98.4% accuracy and 0.988 ROC-AUC on 200K+ evaluation samples. Implemented a real-time Kafka pipeline streaming Zeek DNS logs into a FastAPI inference endpoint, Dockerized for continuous scoring; improved cyber threat detection rate by 40% and reduced manual log-review effort by 60%.
Machine Learning Intern at Maxgen Technologies
June 1, 2022 - June 15, 2022
Acquired foundational skills in ML, data analysis, and Python programming through a 15-day intensive internship; developed a plant disease detection ML model achieving 85% accuracy; optimized model performance via image preprocessing and edge detection.

Education

bachelor of computer engineering at silver oak university
June 1, 2019 - June 1, 2023
Bachelor of Engineering (BE) in Computer Engineering at Oak College of Engineering and Technology
January 1, 2017 - January 1, 2019
Higher Secondary Certificate (12th) at SC Higher Education
January 11, 2030 - April 12, 2026
B.E. Computer Engineering at Silver Oak College of Engineering & Technology
January 1, 2019 - January 1, 2023
B.E. Computer Engineering (CGPA: 8.11/10) at Silver Oak College of Engineering & Technology, Ahmedabad, India
January 1, 2019 - January 1, 2023
B.E. Computer Engineering at Silver Oak College of Engineering & Technology, Ahmedabad, India
January 1, 2019 - January 1, 2023

Qualifications

Prompt Design in Vertex AI
January 11, 2030 - June 21, 2026
Inspect Rich Documents with Gemini Multimodality & Multimodal RAG — Google Cloud Skills Boost
January 11, 2030 - June 21, 2026

Industry Experience

Government, Computers & Electronics, Other, Software & Internet, Education, Professional Services, Telecommunications, Healthcare, Media & Entertainment
    Plant Disease Detection

    Engineered a Plant Disease Detection CNN in PyTorch from scratch during a 15-day program, achieving 90% accuracy via Computer
    Vision, deep learning architecture design, and transfer learning fine-tuning.
    • Boosted accuracy by 10% over baseline through image preprocessing using OpenCV (histogram equalization, edge detection) and
    Reinforcement Learning-inspired hyperparameter optimization.
    • Resolved class imbalance using oversampling and focal loss, demonstrating proficiency in deep learning fine-tuning, image augmentation,
    and production-ready model packaging

    DGA domain detection

    • Built an end-to-end DGA detection system: extracted n-gram/entropy features from 1M+ domain samples, trained a character-embedding
    LSTM in TensorFlow/Keras achieving 98.4% accuracy and 0.988 ROC-AUC on 200K+ evaluation samples.
    • Built a real-time Kafka producer-consumer pipeline streaming Zeek DNS logs (50,000+ entries/session) into a FastAPI inference endpoint,
    Dockerized for continuous scoring; improved cyber threat detection rate by 40% and cut manual log-review effort by 60%.