Hi, I'm Atharv Sakalley, a Generative AI Data Scientist with over six years of experience specializing in building RAG pipelines and AI agent systems. I'm certified in Databricks Generative AI and Snowflake, and I enjoy leveraging my strong Python and ML background to develop, monitor, and deploy production-ready AI solutions. I love working with advanced AI tools and deploying solutions on platforms like AWS Bedrock, OpenSearch, and EC2. I am passionate about creating scalable AI lifecycle management systems and making complex AI workflows efficient and accessible, helping companies optimize their operations and deliver impactful results.

ATHARV SAKALLEY

Hi, I'm Atharv Sakalley, a Generative AI Data Scientist with over six years of experience specializing in building RAG pipelines and AI agent systems. I'm certified in Databricks Generative AI and Snowflake, and I enjoy leveraging my strong Python and ML background to develop, monitor, and deploy production-ready AI solutions. I love working with advanced AI tools and deploying solutions on platforms like AWS Bedrock, OpenSearch, and EC2. I am passionate about creating scalable AI lifecycle management systems and making complex AI workflows efficient and accessible, helping companies optimize their operations and deliver impactful results.

Available to hire

Hi, I’m Atharv Sakalley, a Generative AI Data Scientist with over six years of experience specializing in building RAG pipelines and AI agent systems. I’m certified in Databricks Generative AI and Snowflake, and I enjoy leveraging my strong Python and ML background to develop, monitor, and deploy production-ready AI solutions.

I love working with advanced AI tools and deploying solutions on platforms like AWS Bedrock, OpenSearch, and EC2. I am passionate about creating scalable AI lifecycle management systems and making complex AI workflows efficient and accessible, helping companies optimize their operations and deliver impactful results.

See more

Experience Level

Expert
Expert
Expert
Intermediate

Work Experience

Senior Analytics Engineer at Impetus Technologies
April 1, 2024 - Present
Designed and built Machine Learning models, including LLM, to automate risk prediction, streamlining decision-making processes for improved efficiency. Implemented digital tools, including LLM models for Operational health checks, and utilized Power BI for data analytics, optimizing operational processes and identifying areas for improvement. Maintained and optimized Risk Management using CPPM integrated with SQL and Power BI Dashboards, delivering crucial insights for successful hospital group projects.
Data Scientist at Siemens Healthineers
March 31, 2024 - July 21, 2025
Built an agent-based document extraction system using LangGraph and OpenAI to extract structured data from insurance documents. Developed Excel-to-dictionary converters for semantic field mapping and synonym resolution. Automated prompt repair and reprocessing to improve LLM extraction accuracy with minimal manual review. Created a RAG AI Playground with Streamlit for real-time LLM evaluation across FAISS, Pinecone, Weaviate. Integrated Mosaic AI and MLflow Tracing to track quality, latency, and cost in AI workflows. Deployed LLM solutions on AWS Bedrock, OpenSearch, and EC2 for production use cases, enabling scalable AI lifecycle management using MLflow, Databricks, and MLOps best practices.

Education

MSc at Friedrich-Alexander University Erlangen–Nuremberg, Germany
August 1, 2015 - August 31, 2019
B.Tech at LNCT Group of Colleges, Bhopal
August 1, 2015 - August 31, 2019

Qualifications

Databricks Certified Generative AI Engineer Associate
October 1, 2021 - October 31, 2023
SnowPro Core Certification
August 1, 2024 - August 31, 2026
Oracle Cloud Infrastructure 2024 Generative AI Professional (1Z0-1127-24)
April 1, 2025 - April 30, 2027

Industry Experience

Healthcare, Financial Services, Software & Internet, Professional Services