Tremayne Timms

ML & AI Engineer — Fine-Tuning · Agentic Systems · Edge Deployment · Production LLM Ops

Dallas–Fort Worth, TX

About

I build production LLM systems from the metal up — from quantized models running on Jetson edge hardware to multi-agent cloud deployments with tool-use, permission gating, and audit trails. Currently focused on MoE fine-tuning, Blackwell-native FP4 quantization (NVFP4), and agentic coding benchmarks (SWE-bench).

Current Focus

Where my deep work is going right now.

ZAYA1 NVFP4 W4A4 on Blackwell

4-bit weights and activations for an 8B MoE on a 16 GB RTX 5070 Ti, custom vLLM CUTLASS SM120 source build. HumanEval 72.6% pass@1 (95% CI [65.3, 78.8]) from a 6.02 GB checkpoint, matching or beating published full-precision results for Qwen 3 7B and Llama 3 8B, and apparently the first HumanEval figure for this model at any precision. 9.5 tok/s single-stream / ~74 tok/s batch-8. Also quantified the reasoning/latency tradeoff: disabling the reasoning trace is ~8.5x faster but costs 17 to 29 accuracy points.

Bible AI Assistant

Qwen3.5-4B fine-tuned with ORPO for biblical Q&A — hybrid RAG (ChromaDB + BM25 + cross-encoder reranking), constitutional AI guardrails, and a Whisper + Kokoro voice pipeline behind a Gradio UI. 183 tests, 34 W&B runs.

Sovereign Edge

Autonomous multi-agent personal intelligence on NVIDIA Jetson Orin Nano — 5 LangGraph expert agents, LiteLLM gateway, 3-tier ONNX intent router. Fully on-device, zero cloud dependencies. 415 tests.

Projects

Production-grade systems — every one tested, documented, and shipped.

Godspeed Coding Agent

Security-first coding agent. Async ReAct loop with a 4-tier deny-first permission engine, SHA-256 hash-chained audit trail, and 200+ LLM providers via LiteLLM. SWE-bench Lite (dev-23 split): 34.8% single-shot · 52.2% oracle best-of-5, free-tier drivers.

4,600+ testsMCPLiteLLMGRPO export

Manna Trading

Multi-agent algorithmic trading pipeline with DeepSeek R1 reasoning at every stage. 4-agent pipeline (TA → Chief → Risk → Execution), Kelly Criterion sizing, Monte Carlo risk, real-time WebSocket data.

DeepSeek R1Multi-agentWebSocket

GPU Server Test Suite

Comprehensive GPU fleet validation modeled on NVIDIA DCGM. 16 diagnostic modules, Prometheus + Grafana, fault injection, JUnit XML for CI.

188 testsPrometheusGrafana

ML Lab

ML research control plane — experiment lifecycle management, model registry, and cloud training launcher. Orchestrates preflight checks and knowledge persistence across the stack.

49 testsv0.1.0MLOps

LLM Wiki

Git-backed knowledge base on Karpathy's LLM Wiki pattern. LangGraph ingest/query pipelines, instructor + Pydantic structured output, BM25 search, Groq → Gemini → Ollama fallback.

117 testsLangGraphPydantic

Manufacturing Quality Analytics

SQL + Python ETL pipeline for semiconductor quality analysis — supplier performance scoring, defect Pareto distributions, and yield trend analysis.

SQLETLpandas

Tesla Tire Wear ML

Multi-model ML pipeline for Tesla tire wear prediction. Random Forest, XGBoost, and Neural Network ensemble with Claude AI integration.

XGBoostEnsemblescikit-learn

Open Source

Upstream contributions on cutting-edge inference hardware.

Skills

From kernels to multi-agent orchestration.

LLMs & Agents
LiteLLM, 200+ providers, Ollama, llama.cpp, multi-agent orchestration, ReAct loops
Fine-Tuning
Unsloth, TRL (SFT/DPO/GRPO/ORPO), QLoRA, PEFT, MoE architectures, RLHF/RLAIF
Inference
vLLM (custom forks), speculative decoding (750 tok/s), TensorRT-LLM, EXL2
Quantization
NVFP4 (Blackwell-native), GGUF, EXL2, FP8, NF4, GPTQ, AWQ
ML Infrastructure
PyTorch, CUDA 12.8, torch.compile, DeepSpeed, lm-eval, W&B, MLflow
Systems
Python, Rust, TypeScript, Docker, GitHub Actions CI/CD, systemd
Edge / Hardware
NVIDIA Jetson Orin Nano, RTX 5070 Ti (Blackwell sm_120), 16 GB VRAM optimization
Data
PostgreSQL, SQL, pandas, SQLAlchemy, ChromaDB, LanceDB, BM25