I built and operated a portfolio of independently deployed production systems, standardizing observability while improving reliability, performance, and resource efficiency. For multi-asset, multi-strategy interday equity options, I built a Kubernetes backtesting framework with indexed job scheduling and an autonomous gpt-oss-120b signal-mining agent that identified strategies with Sharpe above 1.5.
I also fine-tuned Amazon Chronos-T5 with LoRA on labels derived from the backtesting engine, then used the resulting embeddings to train per-asset TabPFN classifiers for inference.
For single-stock options systems, I calibrated a jump-, rate-, and dividend-aware stochastic-volatility model to live option-chain snapshots and priced American options with a discrete-dividend binomial correction. Narratives of risk-neutral volatility, jump risk, and expected movement became structured input for gpt-oss-120b trade decisions. An automated daily harness measured reliability, rule compliance, consistency, and robustness.
I also deployed intraday index-options strategies using Bayesian anomaly detection over stochastic-volatility-model forecasts, achieving 5–10% weekly returns on capital at risk.
I deployed a DPO-QLoRA-tuned Llama-3.1-8B and DSPy-backed FX trading system. Its news-relevance pipeline combined BM25, Qwen3 Embedding, reciprocal rank fusion, and Qwen3 Reranker; gpt-oss-20b compressed news and price action into the inference context. Archived contexts were replayed against ground truth to benchmark precision, recall, F1, and coverage, while evaluation-gated GEPA optimization used gpt-oss-120b as the reflection model.
I generated preference pairs with single-node multi-GPU data parallelism and vLLM continuous batching, then fine-tuned a frozen NF4 Llama-3.1-8B base with rank-16 LoRA using multi-node distributed data parallelism. An OpenAI-compatible vLLM endpoint provided versioned adapter promotion and storage-backed rollback.
I built a daily rebalanced, regime-aware equity portfolio using a Hidden Markov Model for regime detection, ElasticNet forecasts, and NSGA-II optimization, achieving 5% annualized alpha in a multi-year backtest. I also shipped a multimodal RAG PDF assistant backed by Qwen3-VL, a two-pass workflow, and Qdrant.
