CURATED ENGINEERING CATALOG
The catalog intentionally surfaces the strongest evidence from a much larger body of work. Flagship systems prove the core career narrative; supporting projects deepen specific technical claims.
RECRUITER VIEWS
18 curated projects shown
Full-stack AI operations platform connecting telemetry, policy, AI investigation, human approval, and evidence replay.
A governed operations platform for regulated environments with a Go operational API, Python AI investigation service, Next.js workspace, OPA policy correlation, audit records, and human-in-the-loop decisions.
Deterministic evaluation, RAG quality, safety red-team testing, regression gates, and fail-closed release evidence.
A production-style Python evaluation platform with provider abstraction, JSONL datasets, prompt boundaries, model comparison, RAG metrics, safety checks, experiment tracking, model aliases, CI gates, and a public release dashboard.
A real backend product moving from job ingestion to explainable, persisted, personalized career recommendations.
An enterprise-style FastAPI platform with PostgreSQL, SQLAlchemy, Alembic, Redis, Docker, company and job services, deterministic scoring, career-profile APIs, personalized matching, persisted evidence, seed data, and smoke tests.
A clinician-controlled AWS healthcare workflow for telehealth intake, transcription, structured chart drafting, approval, and auditability.
A HIPAA-aligned architecture and active build for behavioral-health intake and clinical documentation, combining secure portals, video consultation, medical transcription, speaker separation, structured AI chart drafts, clinician review, encrypted PHI, access controls, audit logging, and EHR/FHIR integration patterns.
The same governed RAG workflow implemented four ways to compare framework behavior fairly rather than compare unrelated demos.
A completed Python engineering lab implementing a shared evidence-review workflow across LangChain, LangGraph, Strands, and ADK-style patterns with common schemas, tools, datasets, benchmark questions, trace envelopes, scoring rubrics, structured outputs, and human-review routing.
Secure cross-application agent action without broad standing privileges or independent superuser authority.
A deterministic Python implementation of user-bound delegation, OAuth 2.0 token-exchange concepts, OIDC claims validation, policy-as-code authorization, scoped delegated tokens, API-side enforcement, abuse-case testing, and evidence records for allow and deny decisions.
Live healthcare RAG and agent evaluation with evidence export, integrity verification, and tamper detection.
A split-deployed healthcare governance demo evaluating groundedness, relevance, citation quality, hallucination risk, policy compliance, and reviewer approval using synthetic scenarios.
Reusable engineering governance for prototypes, CI/CD patterns, evidence generation, and explicit operating boundaries.
A structured platform for producing testable, reviewable accelerators with scope, validation, security assumptions, compliance evidence, and promotion paths.
Founder-MVP-to-production architecture spanning Bedrock, serverless delivery, security, cost controls, and scale paths.
An AWS Startup Solutions Architect-style lab that maps customer outcomes to pragmatic service choices, production hardening, and a staged SaaS and GenAI roadmap.
Build-ready Agent Identity Broker issuing JIT, least-privilege credentials with deterministic OPA enforcement.
A FastAPI and OPA runtime skeleton for machine identity, structured intent, short-lived scoped tokens, and audit evidence at the agent-to-tool boundary.
Simulation-first Copilot governance control plane with schema-backed evidence, CI validation, and doctrine alignment.
A governed domain implementation for Microsoft Copilot adoption covering risk intake, data leakage scenarios, access boundaries, evidence workspaces, and executive reporting.
Data-centric AI readiness workflow for sensitive-data discovery, exposure analysis, risk scoring, and audit evidence.
A synthetic-data-only DSPM platform foundation for GenAI and agent access, including policy rules, a Python API, scoring tests, and executive posture artifacts.
Layered deepfake and impersonation governance using provenance, multiple detection signals, risk scoring, and human review.
A phased control-plane design for image, audio, and video intake, custody, C2PA-style provenance, model checks, quarantine, escalation, and audit records.
Enterprise AI gateway pattern connecting identity, RAG, policy, CMDB, ticketing, audit, approval, and observability.
A modular integration architecture for regulated enterprise workflows, showing how AI can retrieve context, evaluate policy, call systems, and create auditable evidence.
GCP-style enterprise AI delivery model spanning intake, risk tiering, retail integrations, approval gates, observability, and support handoff.
A phased retail architecture for governed AI use cases across POS, inventory, ERP, CRM, supply chain, identity, cost controls, and release operations.
Terraform-driven AWS, Azure, and GCP compute foundations with modular infrastructure and Zero Trust network baselines.
The foundational multi-cloud architecture repository spanning provider-specific network and compute modules, reusable stacks, and deployment symmetry.
Hands-on cross-cloud identity federation covering SAML, OIDC, SCIM, Conditional Access, permission sets, and RBAC.
A complete identity federation learning and implementation path connecting Entra ID to AWS IAM Identity Center with automated provisioning and least-privilege access.
Systems-thinking implementation path for standardizing how agents discover and invoke enterprise tools across platforms.
A focused learning lab explaining tool contracts, adapters, cross-platform routing, and the role of MCP in reusable enterprise agent integration.