Shyam sundar Rampalli - GenAI Engineer

Berlin, Germany

Experience

Aug 2025 - Present

6 months

Berlin, Germany

Hybrid

Built a hybrid semantic and keyword search and LLM-based requirement extraction from conversational queries, boosting search accuracy by 85%, cutting zero-result searches by 70%, and reducing search time by 60%.
Deployed a production-ready API with monitoring dashboards over 100K+ products, keeping response times under 2s and reducing customer search-to-purchase time by 40%.
Technologies: Python, BGE-M3, Qwen2.5, FastAPI, Qdrant, Meilisearch, Docker, Prometheus, vLLM.

Jun 2024 - Jul 2025

1 year 2 months

Lyon, France

Built an NLP pipeline using BERT and Llama 2 to extract and summarize critical information from disaster reports.
Applied LoRA fine-tuning and prompt engineering to adapt models for structured summarization and entity extraction.
Produced concise, real-time summaries, improving incident-processing speed by 40%, reducing manual analysis effort by 55%, and accelerating decision-making latency by 30% across disaster-response workflows.
Technologies: BERT, Llama 2, LoRA, PyTorch, Transformers, AWS, MLflow, FastAPI, Docker, GitHub Actions, CI/CD Pipelines, S3.

Jan 2024 - May 2024

5 months

Bengaluru, India

Built an end-to-end ETL and clickstream A/B testing framework to optimize checkout flows, reducing analysis time by 30%.
Processed ~200k–300k events for funnel and drop-off analysis and trained Random Forest and XGBoost models, achieving a ROC-AUC of 0.82 and 15% higher precision in conversion prediction.
Technologies: Python, Pandas, scikit-learn, XGBoost, Git, AWS Lambda, S3, FastAPI, GitHub Actions, PostgreSQL, Docker.

Nov 2022 - Jan 2024

1 year 3 months

Bengaluru, India

Built a cloud-based AI pipeline using YOLOv6 on SageMaker to automatically detect traffic violations from city video feeds, improving detection accuracy by 30% and vehicle identification by 21%.
Automated video processing with Lambda triggers for inference on new S3 uploads and real-time aggregation of results.
Added a GDPR-compliant anonymization plugin that masks faces and license plates using YOLOv6 and OpenCV, ensuring privacy while maintaining analytics accuracy.
Streamlined model updates and deployment with CI/CD, ensuring consistent and scalable operations.
Technologies: Python, YOLOv6, PyTorch, OpenCV, AWS Lambda, S3, SageMaker, CI/CD, GitHub Actions, Docker, FastAPI.

Sep 2021 - Oct 2022

1 year 2 months

Singapore

Developed real-time traffic dashboards using city-wide camera feeds, enabling planners to monitor traffic flow and congestion effectively.
Processed data from 11 urban locations and generated actionable insights for traffic management.
Applied unsupervised clustering on GPS data to identify travel patterns, contributing to 15% cost savings in public transit planning.
Technologies: Python, Matplotlib, Plotly, PostgreSQL.

Oct 2019 - Sep 2021

2 years

Singapore

Analyzed GPS data from a bike-sharing service to improve user satisfaction and operational efficiency.
Increased bike-sharing usage time by 18% through pattern recognition and optimized service allocations.
Designed interactive dashboards using Plotly for real-time performance tracking.
Technologies: Python, SQL, Plotly, Data Analysis.