Geddy Dukes

Geddy Dukes

AI/ML systems engineer who builds production ML infrastructure from first principles. Implemented a 67M-parameter language model from scratch, multimodal self-supervised learning systems (JEPA/CPC), and neuro-symbolic AI frameworks. Published open-source agent runtime on npm. Deep experience in full-stack development, LLM orchestration, and production deployment. Domain expertise in financial systems, real estate, and regulated environments.

Featured Projects

Deep Learning Research

TinyLLM - Language Model from Scratch

live

67M parameter transformer with continual learning system

PythonPyTorchWandB

Implemented a 67M parameter transformer from scratch, featuring a custom continual learning system to prevent catastrophic forgetting.

  • 67M Parameters
  • Continual Learning
  • Transformer Architecture

World Model - Multimodal Self-Supervised Learning

live

JEPA + CPC + CLIP implementation with episodic memory

PythonPyTorchJEPACPCNumPy

Vision–audio contrastive learning with episodic memory; nightly training/validation and rollout evaluation to test temporal dynamics and embedding coherence.

  • JEPA + CPC + CLIP
  • Episodic Memory
  • Self-Supervised

AI Infrastructure & Frameworks

Daedelos SDK - Neuro-Symbolic AI Platform

deploying

Enterprise AI governance with audit trails and hybrid reasoning

PythonFastAPIPostgreSQLpgvectorRedis

Hybrid multi-agent framework that composes deterministic symbolic rules with LLM agents for explainable, traceable decisions in regulated contexts.

  • Neuro-Symbolic
  • Audit Trails
  • Hybrid Reasoning

Feather Agent - Open-Source Agent Runtime

live

Provider-agnostic agent framework (published on npm)

TypeScriptNode.js

Open-source runtime for stateful agents, tool execution, model routing, and transparent streaming plans with config-driven state/behavior/lifecycle.

  • Provider-Agnostic
  • npm Package
  • Agent Runtime

agentbench – Open-Source Agent Evaluation Framework

live

Framework for benchmarking LLM and tool-using agents

PythonAsyncIO

Framework for benchmarking LLM and tool-using agents. Supports async execution, retries, rate limits, composite judges, JSONL artifacts, traces, and HTML reports.

  • Agent Benchmarking
  • Open Source
  • Python Package
  • Report Generation

Full Stack Applications

Audio Routing System - Hybrid ML + Rules

live

Intelligent audio classification and dynamic stem routing

PythonDSP/ML

Ingests multi-track audio events (speech/SFX/music), classifies via rule + ML, and dynamically routes stems through a virtual post-production graph.

  • Hybrid ML + Rules
  • Dynamic Routing
  • Audio Classification

Financial Analysis Platform

live

Real-time underwriting metrics with RBAC + audit

Next.jsTypeScriptPostgreSQLSupabaseNode.js

Underwriting workflow platform processing millions in loan volume; 15+ metrics with sub-second latency, RBAC, audit logs, and secure APIs.

  • Sub-second calc engine
  • Compliance-ready
  • Used in production

Professional Experience

Credit Analyst & Program Manager, Catalytic Capital

Community Vision Capital & Consulting

Dec 2023 – Nov 2025 · Remote

  • Built a financial spreading platform (TypeScript/Next.js/PostgreSQL/Supabase) with RBAC, audit logs, and real-time pipelines used by underwriting teams.
  • Encoded complex financial rules as reliable backend logic across automated workflows.
  • Managed $30M program and underwrote deals up to $3M; integrated lending logic into internal tooling.
Highlight

Finance → software builder: moved complex rules into auditable, real workflows.

Catalytic Capital Program Analyst

Community Vision

Jun 2022 – Dec 2023

  • Improved program efficiency ~20% via data models and analysis.
  • Coordinated budgeting/performance across ~$100M in programs; managed AHP/AHEAD compliance cycles.

Finance Project Manager

Dorjil Company

May 2020 – Oct 2021

  • Built Python/SQL tools securing $400K+ in subsidies; automated data pipelines for ~25% efficiency.
  • Led multi-year audit recovering $2M in overdue operating subsidies.

Full-Stack Software Engineer

Blindly (contract)

Jun 2020 – Sep 2020

  • Implemented ID parsing/verification (Node/React/Redux) and shipped authentication flows in a cross-functional team.

Core Skills

Engineering

TypeScriptPythonNode.jsReact/Next.jsReact NativeSQL (PostgreSQL + Supabase)DockerAWSVercelGit/CI/CD

AI Systems

LLM orchestrationagent frameworksRAGsymbolic–LLM hybridsembeddings & vector searchmulti-agent coordinationmultimodal SSL (PyTorch)

Delivery & Leadership

Agile/Scrumprogram leadershiprisk analysisstakeholder alignmentauditability & compliance design

Get In Touch

Open to in person roles in the SF Bay Area and remote opportunities