Skip to content
View sanjayatb's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report sanjayatb

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sanjayatb/README.md

Sanjaya Rajamantri

12+ years building distributed, real-time systems at the intersection of financial data and machine learning.

What I build

  • Real-time data pipelines at financial scale — Kafka, Flink, Spark, ClickHouse
  • ML platforms for anomaly detection and pattern recognition
  • Agentic AI systems and LLM-powered developer tooling
  • Low-latency complex event processing engines (C++)

Background

  • London Stock Exchange Group (LSEG) — Next-gen capital market surveillance stack, ML platform for anomaly detection, C++ pattern detection framework
  • Binance — Core data platform infrastructure at petabyte scale, open-source query engine contributions, early LLM-to-SQL feasibility (2020)
  • Credit Agricole CIB — Real-time payment systems, high-throughput streaming architecture
  • WirelessCar — AI Evangelist, agentic engineering, Codex/Copilot/Claude adoption

Education

  • MSc Data Science & AI — Chalmers University of Technology (GNN, Fourier Neural Operators, Applied ML, Distributed Systems)
  • BSc Engineering (Hons) — University of Moratuwa
  • IEEE Published Researcher — DSP 2014, Hong Kong

Core stack

Languages   Rust · Java · Python · C++ · Scala · JavaScript 
Big Data    Kafka · Spark · Flink · HBase · ClickHouse · Presto · Hive · ElasticSearch
ML          TensorFlow · Keras · scikit-learn · PyTorch · Pandas · Scipy · GNN · FNO · PointNet
Cloud       AWS (Certified SA) · Docker · Kubernetes · Terraform · Cloudformation
AI Tools    Claude · Codex · Copilot · LangChain
Frameworks  Spring Cloud · Spring Boot · Vert.x

Currently focused on

Real-time AI systems for on-chain risk intelligence —
anomaly detection, graph-based contagion modelling,
and LLM-powered monitoring at blockchain scale.

Research

📄 Speaker Verification for Forensic Evidence Evaluation
IEEE DSP 2014, Hong Kong — MFCC feature extraction, GMM probabilistic modelling

Connect

LinkedIn

Pinned Loading

  1. Kaggle Kaggle Public

    Kaggle Notebooks (Kernels)

    Jupyter Notebook 1

  2. spark-mq spark-mq Public

    MQ source for spark structured streaming

    Java 1 1

  3. cfd-aero-pytorch cfd-aero-pytorch Public

    CFD simulation test repo

    Python 1

  4. blockchain-data-feeds-poc blockchain-data-feeds-poc Public

    Go

  5. DrivAerNet-Aero DrivAerNet-Aero Public

    Forked from Mohamedelrefaie/DrivAerNet

    A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

    Python

  6. incubator-linkis incubator-linkis Public

    Forked from apache/linkis

    Linkis helps easily connect to various back-end computation/storage engines(Spark, Python, TiDB...), exposes various interfaces(REST, JDBC, Java ...), with multi-tenancy, high performance, and reso…

    Java