TRAINING
→Forward Pass
LOSS
2.4000
ACC
12.0%
EPOCH
0
lr: 3.0e-4∇: 1.200
RSI TECH
WorkAboutContactGitHub
RSI TECH

Quantitative systems & applied AI -- shipped.

We build LLM-augmented intelligence platforms, anomaly detection at scale, optimization workflows, and performance-oriented infrastructure.

Explore workContact
Signal over noise. Auditability over hype.

Selected Work

PROGRAM | Security Analytics | 2019 -> 2022

Security Ops: User Behavior Analytics & Anomaly Detection

Large-scale telemetry -> behavioral baselines -> explainable anomaly signals for SOC workflows.

PySparkPythonUnsupervised learningFeature engineeringLog pipelines
  • Processed enterprise telemetry streams (directory, proxy, endpoint) at scale.
  • Unsupervised detection to surface meaningful anomalies with controllable false positives.
  • Analyst-in-the-loop iteration and methodology docs to keep the system auditable.
PROGRAM | Data Platforms | 2021 -> 2022

Automated Time-Series Forecasting Framework

Benchmark -> train -> evaluate -> iterate, with repeatable objectives.

PythonTime-seriesModel benchmarkingReproducible pipelines
  • Semi-automatic end-to-end forecasting workflow with consistent evaluation.
  • Model benchmarking across candidate families under realistic constraints.
  • Designed to be rerun safely (same inputs -> comparable outputs).
PROGRAM | Data Platforms | 2022 -> 2025

Marketing Analytics & Incremental Lift Optimization

Decision-grade measurement and targeting models aligned to incrementality, not vanity metrics.

PythonPredictive modelingTargetingExperimentation mindsetProduction integration
  • Incremental Return on Ad Spend (iROAS) analytics for budget decisions.
  • CLTV, propensity, and look-alike models for targeting efficiency.
  • Insight -> recommendation workflows for partners and stakeholders.
PROGRAM | LLM Systems | 2025 -> now

Career Survey Intelligence & Compensation Consistency Engine

LLM-augmented analytics + optimization for high-stakes workflows.

PythonLLM pipelinesOptimizationHybrid rules+MLEvaluation/monitoring
  • Parse and normalize free-text roles/narratives into structured signals.
  • Detect compensation and seniority inconsistencies with explainable rationales.
  • Hybrid design: quantitative models + rules + LLM output grounding.
LAB | Quant & Trading | ongoing

Quant R&D Platform & Rust-backed Services

Research-to-production trading workflows with performance and risk constraints as first-class features.

RustPythonBacktestingTime-seriesRisk constraints
  • Backtesting and signal evaluation discipline designed to resist overfitting.
  • Performance-oriented services where latency and throughput matter.
  • Architecture that keeps audit trails and constraints explicit.
Details are generalized for confidentiality. See the full index in /work.

Capabilities

LLM Systems
  • RAG + structured extraction
  • Evaluation discipline + regression checks
  • Hybrid grounding with domain constraints
Quant & Trading
  • Research harnesses + backtesting
  • Risk-aware primitives
  • Rust-backed performance services
Data Platforms
  • Forecasting automation
  • Targeting and optimization loops
  • Production integration
Security Analytics
  • UBA and anomaly detection
  • Telemetry pipelines at scale
  • Analyst-friendly explainability