Projects
A collection of infrastructure projects, platform engineering solutions, and ML systems I've built to solve real-world problems at scale.
Filter by Technology & Domain
Aether
A production-ready Safe GenAI Platform integrating content safety, traffic governance, ML inference, and real-time observability into a unified system.
- Unified Architecture: Orchestrates Sentinel, Atlas, Hyperion, and MonitorX into a cohesive GenAI platform.
- End-to-End Safety: Every request passes through content moderation before and after inference.
- Production Observability: Real-time metrics, alerting, and dashboards for complete visibility.
- One-Command Deploy: Docker Compose setup brings up the entire stack with health checks and dependencies.
Sentinel
A production-grade AI supervision layer that acts as a firewall for LLMs. Enforces compliance, safety, and quality standards in real-time.
- Hybrid Supervision Strategy: Implements tiered defense architecture (Layer 1 Regex/Presidio -> Layer 2 BERT -> Layer 3 LLM-as-a-Judge) to optimize latency, API cost, and accuracy simultaneously.
- High-Performance Compliance: Reduces PII escape rates by 99.9% while adding <5ms latency at P95 using deterministic heuristics before falling back to heavy ML models.
- Pluggable Policies: Define custom compliance rules for Healthcare (HIPAA), Finance, or Brand Tone without retraining models.
- SaaS Architecture: Built with a secure API Gateway pattern using RapidAPI and Google Cloud Run. Fully integrated billing and quota management system.
Atlas
A sophisticated LLM traffic and quota management gateway built with Redis, FastAPI, and Prometheus. Enables intelligent model routing, request limiting, and comprehensive observability for AI applications at scale.
Key Features:
- Real-time quota management and rate limiting
- Intelligent model routing based on load and cost
- Comprehensive metrics and monitoring
- High-performance async architecture
Guardian
A semantic firewall for Autonomous Agents. Intercepts and validates tool calls, analyzes generated code (AST), and enforces business logic policies before execution.
- Agent Governance & OWASP Compliance: A semantic firewall mitigating the OWASP Top 10 for LLMs (e.g., Prompt Injection, Insecure Output Handling, and Overreliance) in autonomous agents.
- High-Availability AST Analysis: Statically and safely analyzes dynamically generated Python code for forbidden imports or syscalls in <2ms, unblocking massively parallel execution.
- Durable Workflows & Policy-as-Code: Dynamic rule engine to enforce strict enterprise business logic (e.g., “No refunds > $100”) ensuring safe tool-calling behavior in non-deterministic systems.
- Defense-In-Depth Integration: Seamless integration with Sentinel for content safety, providing full-stack, multimodal security across the orchestration loop.
Hyperion
High-performance ML inference platform with GPU acceleration and intelligent request batching. Achieves 10-50ms inference times with 10x+ throughput improvements through dynamic batching and Kubernetes-native autoscaling.
Key Performance Features:
- GPU acceleration: 10-50ms inference times (10x faster than CPU)
- Intelligent batching: 10x+ throughput with dynamic batch sizes
- Advanced Kubernetes scaling: HPA, VPA, and KEDA support
- Production monitoring: Prometheus metrics and real-time observability
System Metrics
Strategos
A durable agent orchestration engine. Features an event-sourced workflow kernel, tiered context memory, and Model Context Protocol (MCP) integration.
- Durable Execution: Event-sourced workflow engine that survives infrastructure failures.
- Cognitive Architecture: Pluggable reasoning loops (ReAct, Plan-and-Solve) decoupled from the runtime.
- MCP Integration: Native support for the Model Context Protocol to standardize tool connectivity.
- Context Virtualization: Automatic tiering of agent memory (Working Memory vs. Vector Storage).
MonitorX
Comprehensive ML/AI infrastructure observability platform with zero-code monitoring, intelligent alerting, and real-time drift detection. Provides complete visibility into production ML systems with enterprise-grade dashboards and automated model health monitoring.
Key Features:
- Real-time model performance monitoring and drift detection
- Intelligent multi-channel alerting with automated remediation
- Interactive dashboards with A/B testing and model comparison
- Cost optimization insights and resource utilization tracking
MonitorX Dashboard
AerialView
Interactive stock market analytics dashboard with real-time visualizations, candlestick charts, and technical indicators powered by Streamlit.
Technology Stack
Technologies and tools I use to build scalable, reliable systems