
Divyansh Shrivastav
@divyanshshrivastava
I build production agentic AI platforms on governed data infrastructure for high-stakes business decisions.
What I'm looking for
At Real Madrid, I designed and shipped ClubOS, a production multi-agent AI platform used by senior stakeholders for monthly commercial decision-making. Built on LangGraph, Databricks, FastAPI, React, and GCP Cloud Run, it processes 59 business metrics across five platforms and includes 604 automated tests.
I built four orchestrated agents for retrieval, anomaly detection, investigation, and executive briefing, with evidence traceability and a guardrail that rejects fabricated numerical claims. I also built ScoutIQ, a football scouting intelligence platform covering 15,000+ players across five leagues.
Previously at HashedIn by Deloitte, I led a four-engineer team delivering an AWS lakehouse on Apache Iceberg, introduced production RAG with Amazon Bedrock, and built Kafka CDC pipelines that reduced reporting latency from 24-hour batches to sub-hour SLAs. I improved Databricks and PySpark job execution time by 40% and helped reduce production regression defects by 30% through dbt testing standards.
At Honeywell, I engineered high-volume pipelines for 1,000+ connected sources, improving distributed query performance by 35% while supporting predictive-maintenance analytics. I build AI on governed, reliable data systems rather than using LLMs where deterministic SQL or Python is the better answer.
Experience
Work history, roles, and key accomplishments
Owned the problem end-to-end: understood the business challenge, designed the architecture, and shipped ClubOS — a multi-agent agentic AI platform deployed on GCP Cloud Run, used by senior club stakeholders for monthly commercial decision-making.
ClubOS processes 59 business metrics across 5 digital platforms, benchmarks Real Madrid against 5 elite European clubs, and produces a deterministic ran
Tech Lead for a 4-engineer team delivering an AWS cloud data lakehouse (S3, Glue, EMR, Lake Formation) for enterprise clients — governed multi-zone Apache Iceberg layout (raw → curated → semantic) accelerating data discovery for 6+ cross-functional teams with column-level security and full lineage tracking via dbt.
✦ Deployed RAG pipeline using Amazon Bedrock for internal knowledge Q&A — designed
Big Data Engineer
Oct 2019 - May 2021 (1 year 7 months)
Engineered high-volume production data pipelines processing streams from 1,000+ connected sources — owned end-to-end ingestion from Oracle and MySQL into HDFS using Hadoop, Hive, and Sqoop with automated schema validation and deduplication at source.
✦ Boosted distributed query performance by 35% through strategic partitioning, bucketing, and YARN cluster tuning — same performance engineering pri
Education
Degrees, certifications, and relevant coursework
Universidad Europea de Madrid
Master's Degree, Sports Analytics
2025 - 2026
Activities and societies: Real Madrid Internship: Designed and shipped ClubOS, a multi-agent AI platform. Final Project: ScoutIQ, a football scouting platform with 15,000+ players and AI assistant.
Pursuing a Master's Degree in Sports Analytics, including a Real Madrid internship where I shipped ClubOS, a multi-agent AI platform. Final project: ScoutIQ, a production-grade football scouting intelligence platform.
Institute for Advanced Computing and Software Development
Post Graduate Diploma, Big Data and Analytics
2019 - 2019
Completed a post-graduate diploma in Big Data and Analytics.
I.T.M Universe ,Gwalior
Bachelor of Engineering - BE, Mechanical Engineering
2014 - 2018
Kendriya Vidyalaya
high secondary school , Physics
2002 - 2014
Tech stack
Software and tools used professionally
Apache Spark
AWS Glue
Google Cloud Platform
GitHub
GitLab
Kubernetes
GitHub Actions
GitLab CI
PySpark
dbt
DB
Sqoop
MySQL
Hadoop
Yarn
Databricks
Terraform
React
Python
Kafka
FastAPI
Grafana
Docker
Airflow
GuardRails
Amazon Web Services (AWS)
Microsoft Power BI
SQL
Apache Iceberg
LangChain
ChromaDB
Pydantic
Delta Lake
OpenAI API
Agentic
LangGraph
LangSmith
Model Context Protocol (MCP)
Column
Availability
Location
Authorized to work in
Portfolio
divyyansh05.github.io/divyyansh05Job categories
Skills
Interested in hiring Divyansh?
You can contact Divyansh and 90k+ other talented remote workers on Himalayas.
Message DivyanshGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
