Skip to content
View schrodingerkitkat's full-sized avatar
1 follower · 4 following

Block or report schrodingerkitkat

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
schrodingerkitkat/README.md

Hello there, I’m Katherine 👋

I’m a Senior Data Engineer & AI Engineer on a mission to transform complex data into intelligent, production-grade systems that redefine what's possible. My playground spans AWS ✕ MLOps ✕ Multimodal LLMs ✕ Real-time Streaming ✕ Autonomous Robotics, and I’m perpetually chasing the next big thing.

Location: LA

Top Languages Profile Views

Actively Building & Researching

  • Multimodal LLM Agents & Orchestration: A Slack-native agent translating natural language into optimized Snowflake SQL through a frontier LLM ensemble, with Milvus vector search and an adaptive feedback loop.
  • Low-Latency Transformer Inference: Benchmarking TensorRT-LLM & vLLM on AWS Inferentia 2 to hit <50ms P95 response times for real-time applications.
  • Autonomous Drone Navigation: Fusing YOLO11, ORB-SLAM3, and custom PX4 flight control on my DJI “Aurelia” for object-aware path planning.
  • Event-Driven Data Mesh: Re-architecting a monolithic Slack→Athena pipeline into Kafka/EventBridge microservices with Polars & OpenTelemetry.
  • Topological Data Analysis: Using persistent homology & Mapper to surface hidden structural features in high-dimensional social engagement graphs.

🔭 Featured Projects

Personalized Mental-Health App Recommender

Scalable engine predicting impactful wellness content (meditations, sleep stories) per user.

AWS S3 GCS Airflow PySpark MLlib TensorFlow Terraform

Social Media Comment Sentiment Analysis

NLP pipeline delivering sentiment, emotion & ABSA insights across millions of comments.

HuggingFace Transformers FastAPI Neo4j Docker

Marine Traffic Data Pipeline

PySpark + Flask app streaming MarineTraffic API data into SQL Server & Folium maps.

PySpark Flask SQL Server Folium MarineTraffic API

🛠️ Tech & Toolbox

Languages:
Python Rust SQL

Cloud & Infra:
AWS GCP Docker Kubernetes Terraform

Data & ML:
Kafka Spark Polars TensorFlow PyTorch Hugging Face

Popular repositories Loading

  1. quantum_etl quantum_etl Public

    QuantumETL is a cutting-edge data engineering framework that harnesses the power of quantum-inspired algorithms to optimize complex ETL (Extract, Transform, Load) workflows. By leveraging a hybrid …

    Python 1

  2. tps_parser tps_parser Public

    Read and write to .tps files

    Python

  3. boat_eta boat_eta Public

    Pyspark: DE/AE. Fetches boat locations and etas to a port and creates a map viz

    Python

  4. csv_processor csv_processor Public

    Python

  5. KoalaSis_Processor KoalaSis_Processor Public

    'Efficient Data Processing and Transformation Pipeline for KoalaSis Student Demographics and Enrollment Information

    Python

  6. TextractChemComp TextractChemComp Public

    Extracting chemical composition data from PDF documents, processing the data in AWS using boto3, s3, and Textract, and then loading it into a SQL database.

    Python