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

Highlights

  • Pro

Block or report rjleggieri

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
rjleggieri/README.md

Robert "B.J." Leggieri

Technology leader building practical, secure, and auditable AI systems.

I bring over two decades of systems ownership to applied AI and ML engineering across language, speech, vision, and enterprise data, backed by an M.S. in Artificial Intelligence from UT Austin.

Selected work

  • BQE CORE AI Data Connector: Read-only BQE CORE ingestion, an auditable SQLite warehouse, and traceable planning exports for human-reviewed AI-assisted workload analysis.
  • text-prosody-evidence: Dataset-neutral reference methods for leakage-aware affect evaluation, calibration, reliability, provenance, and auditable evidence.
  • PraxiCom: Archived 2025 UT Austin NURSING-AI Challenge prototype for faculty-directed, voice-based clinical communication practice.
  • Applied AI portfolio: Project context, architecture, results, graduate coursework, and professional background.

Current focus

  • Applied AI and ML engineering
  • Human-centered and multimodal systems
  • Secure data pipelines and AI-ready enterprise data
  • Evaluation, interpretability, and evidence that can be audited

Portfolio | LinkedIn

Pinned Loading

  1. text-prosody-evidence text-prosody-evidence Public

    Evidence-aware reference methods for text and speech affect components

    Python 2

  2. bqe-core-ai-data-connector bqe-core-ai-data-connector Public

    Read-only BQE CORE ingestion, an auditable SQLite warehouse, and AI-ready planning exports. OAuth PKCE; read:core only.

    Python

  3. ut-nursing-ai ut-nursing-ai Public archive

    PraxiCom (formerly CareSpeak) is an affect-aware conversational simulation platform for APRN training, developed for UT Austin's NURSING-AI Challenge.

    TypeScript