Sambit Baliarsingh

About Sambit Baliarsingh

My work sits at the intersection of AI/ML and large-scale data systems, where I focus on taking ideas from concept → architecture → production → scale.AI & Applied ML SystemsBuilt Genesis, an LLM-powered system that converts natural language into SQL and ETL /Spark workflows across 100K+ tables, improving data accessibility and developer productivityDesigned AI-driven systems to analyze Spark workloads (logs + code) and automatically detect inefficiencies, reducing memory usage (~30–50%) and improving performanceExploring agentic workflows to automate debugging, optimization, and decision-making across data platformsLarge-Scale Data SystemsLed development of distributed data systems processing billions of events/day, driving architecture, execution, and production reliabilityDesigned scalable streaming + batch architectures supporting both real-time and analytical workloadsDrove 20–40% cost reduction by optimizing Spark workloads, resource utilization, and eliminating inefficient compute patternsPlatform & Engineering EnablementLed development of In house tool called Neptune Airflow capabilities, improving workflow reliability, standardization, and deployment quality across teamsBootstrapped internal systems for deployment, lineage, and governance, improving developer productivity and operational consistencyLeadership & ImpactLead cross-team initiatives spanning data, platform, and AI systems — aligning technical solutions with business outcomesMentor engineers on system design, debugging distributed systems, and building production-grade ML/data systemsDrive improvements in incident response, deployment quality, and engineering standards, reducing recurring production issues

Experience

1. Staff Engineer

   Walmart Global Tech India

   Feb 2025 — Present

   Fast API, GPT, Chat bot, lineage tracking, AI implementation using GPT for the data governance, meta data management, automation for Sams club retail. Implementation of Milvus and Qdrant.Agentic AI.

Education

• BIJU PATNAIK UNIVERSITY OF TECHNOLOGY

  Bachelor of Technology (BTech), ELECTRONICS AND TELECOMMUNICATION

  2004 — 2008

• Birla Institute of Technology and Science, Pilani

  Master of Technology - MTech, Data Science and Machine Learning

  2021 — 2023

Skills

• Open Source Software
• Javase
• Hadoop
• Gsm
• Big Data
• Pdh
• Sdh
• Core Java
• Jasper Reports
• Oracle Reports
• Integration
• Obiee
• Agile Methodologies
• Software Development
• Odi
• Unix
• Oracle Applications
• Databases
• Jasper
• Oracle Sql Developer
• Performance Testing
• Microsoft Sql Server
• Sql
• Pl/Sql
• Oracle
• Performance Tuning