Skip to content
View David-Antolick's full-sized avatar
1 follower · 2 following

Block or report David-Antolick

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
David-Antolick/README.md

Hi, I'm David

AI/ML engineer building production agentic systems, RAG pipelines, and LLM evaluation infrastructure.

Currently: AI and Platform Engineer at Johnson & Johnson, deploying multi-agent chatbots and data pipelines in regulated pharma manufacturing. Independently built and shipped ClimbSpeed — a full-stack RAG platform with a custom ReAct agent, hybrid retrieval, and eval-driven iteration (4.86/5.0 correctness, 230 benchmarked questions).

What I work on:

  • Agentic AI systems — custom ReAct frameworks, tool calling, multi-agent orchestration
  • RAG pipelines — hybrid retrieval (semantic + BM25 + RRF), eval-driven optimization
  • Data engineering — PySpark, Databricks, Delta Lake, ETL at scale
  • Full-stack — Next.js, FastAPI, PostgreSQL, Docker, SSE streaming

Background in computational biology (MS Pitt, BS RPI) — I've trained protein language models, built bioinformatics pipelines, and run molecular dynamics simulations, but my day-to-day is shipping AI systems that solve challenging problems reguardless of domain.

antolick.ai

Pinned Loading

  1. antolick_website antolick_website Public

    Personal portfolio and e-resume built with Next.js 16, React 19, and Tailwind CSS 4. Hosted at antolick.ai

    TypeScript

  2. REX_voice_assistant REX_voice_assistant Public

    Lightweight offline voice assistant for hands-free music control (YouTube Music Desktop, Spotify) and screen clipping (SteelSeries GG). Runs 100% locally with Whisper speech recognition. No cloud, …

    Python 1

  3. IDG-DREAM-Drug-Kinase-Binding-Prediction-Challenge IDG-DREAM-Drug-Kinase-Binding-Prediction-Challenge Public

    Predicting drug-kinase binding affinity using ESM-2 protein embeddings and XGBoost with Bayesian hyperparameter optimization

    Python

  4. smiling_autoencoder smiling_autoencoder Public

    Character-level VAE for generating novel drug-like molecules from SMILES strings using PyTorch and RDKit

    Python

  5. structure-embeddings-dms structure-embeddings-dms Public

    Evaluating ESM-2 protein embeddings for variant effect prediction against Deep Mutational Scanning fitness scores

    Python

  6. intron-retention-analysis intron-retention-analysis Public

    Bioinformatics pipeline for intron retention analysis, Ensembl annotation enrichment, NMD prediction, and publication-quality visualization

    Python