Skip to content
View leela56's full-sized avatar
0 followers · 3 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report leela56

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
leela56/README.md

Hi, I'm Leela 👋

I'm a data and AI engineer focused on building end-to-end data pipelines and LLM-powered applications — from real-time Kafka streams to agentic AI systems with clinical-grade logic.

What I Build

  • Real-time streaming pipelines — Kafka ingestion, rolling feature engineering, event-driven architectures
    • LLM agent systems — structured AI decision-making with Anthropic Claude, JSON outputs, chain-of-thought reasoning

      • Full-stack data products — FastAPI backends, Next.js dashboards, PostgreSQL/Supabase storage

        • Data engineering foundations — PySpark, Databricks, SQL, pandas, MLflow

        Featured Projects

        Project What It Does Stack
        Sepsis Watchtower Real-time ICU monitoring system using an LLM agent to detect early sepsis risk from live patient vitals Kafka · Claude API · FastAPI · Next.js · Supabase
        ICU Deterioration Agent Streaming agentic AI that detects patient deterioration using Sepsis-3 clinical criteria Python · Anthropic SDK · Streaming
        Automation Agents Monorepo of local agents — job application automation, email drafting Python · Gmail API
        Formula 1 + Databricks End-to-end data engineering pipeline processing F1 race data PySpark · Databricks · Delta Lake

        Tech Stack

        Languages: Python · TypeScript · SQL Data & Streaming: Apache Spark · Kafka · Pandas · MLflow AI/ML: Anthropic Claude API · LLM Agents · Structured Outputs Backend: FastAPI · Flask · REST APIs Frontend: Next.js · React · TailwindCSS Cloud & DB: Databricks · Supabase · PostgreSQL · Railway · Vercel

        📫 LinkedIn · Open to data engineering and AI/ML engineering roles

Pinned Loading

  1. apache-spark apache-spark Public

    PySpark data pipeline with CI/CD (Jenkinsfile), pytest test suite, and structured batch processing

    Python

  2. f1-databricks f1-databricks Public

    End-to-end Formula 1 data engineering pipeline built on Databricks and PySpark with Delta Lake

    Python

  3. agents agents Public

    Monorepo of local automation agents: job search automation and email drafting using LLMs

    Python

  4. health-sage health-sage Public

    Agentic AI pipeline for real-time ICU patient deterioration detection using LLM streaming and clinical scoring

    Python

  5. icu_deterioration_detection_agentic_streaming icu_deterioration_detection_agentic_streaming Public

    Single-file agentic streaming app for real-time ICU patient deterioration detection using Anthropic Claude

    Python

  6. sepsis-risk-dashboard sepsis-risk-dashboard Public

    Real-time ICU monitoring system using an LLM agent (Claude) to detect early sepsis risk from live patient vitals

    Python