AI Reliability Engineering is the discipline of making AI agents trustworthy in production. Creator of Qualixar — 10 open-source tools and 7 peer-reviewed papers covering memory, orchestration, testing, contracts, and security for agent systems that ship.
Experience
Senior Manager & Solution Architect
Leading digital transformation programs for Fortune 500 European enterprises. Managing 100+ member teams across multiple concurrent projects. End-to-end solutioning with GenAI and Agentic AI.
5× Global Technology Innovation Award Winner (2021–2025). Built AI platforms for automated voice dubbing, sound effects generation, and video production — recognized in national media.
Software Engineer
Enterprise solution development for major US telecom and banking institutions.
Software Engineer
Digital platform development for global retail and telecom enterprises.
Network Engineer
Where the journey began — building networking infrastructure for telecom carriers.
Technical Expertise
Cloud & Infrastructure
Digital Experience
Commerce
Backend
Frontend
AI & ML
Architecture
Education
Dual Degree: B.Tech (Engineering) + LLB (Law)
Beyond the enterprise day job, I run Qualixar — an independent AI research initiative. 10 tools, 7 published papers, 1,980 experiment sessions. Building the infrastructure AI agents need to be trustworthy.
Qualixar — The AI Reliability Engineering Platform
10 research-backed tools for building, testing, securing, and governing autonomous AI agents. 5 live · 1 shipping soon · 5 in research.
Design-by-Contract for AI Agents
Formal specification and runtime enforcement of behavioral contracts for autonomous AI agents. Prevents drift, ensures compliance, enables composition.
Supply Chain Security for AI Agent Skills
Static analysis, behavioral sandboxing, and cryptographic attestation for the AI agent skill ecosystem. Detects malicious skills before they execute.
Information-Geometric Memory for AI Agents
Local-first AI agent memory with mathematical foundations. 74.8% on LoCoMo without cloud dependency — highest local-first score reported. Fisher-Rao retrieval, sheaf cohomology, Langevin lifecycle. EU AI Act compliant.
Peer-to-peer communication layer for AI coding agents
P2P agent communication with 8 MCP tools. Agents discover each other, send messages, share state, and lock files. Works with any MCP-compatible agent. SQLite + UDS for <100ms delivery. 480 tests, 100% coverage.
The World's First MCP Gateway That Learns
One hub process, every MCP server, every AI client. 430+ tools exposed through 3 meta-tools — 79% fewer processes, 150K tokens saved per session. Federated tool discovery with shared cache, cost telemetry, and retrieval learning.
AI Reliability Engineering — The Universal Runtime for AI Agents
Orchestration runtime of the Qualixar AI Reliability Engineering platform. 13 execution topologies (sequential, parallel, debate, mesh, hybrid, and more), Forge AI auto-design, adversarial judge pipeline, cost-quality-latency routing. 2,936 tests passing. Paper on arXiv.
Regression Testing for Non-Deterministic AI Agents
Token-efficient stochastic behavioral testing framework purpose-built for non-deterministic AI agent workflows. Part of the Qualixar AI Reliability Engineering platform.
Runtime Amplification Layer for AI Coding Agents
Five deterministic Claude Code hooks add dynamic effort routing, goal anchoring, convergence detection, persona escalation, and token budgeting. Cross-host: Claude Code, Cursor, GitHub Copilot, LangGraph, CrewAI, AgentScope, LangChain. Zero extra LLM calls. Part of the Qualixar AI Reliability Engineering platform.
Multi-agent communication degradation benchmarking.
Reliability analysis for AI-generated code.
Time-travel debugging for autonomous agents.
Chaos engineering principles applied to AI agent systems.
Migration engineering across agent frameworks.
Composition testing for agent pipelines.
Published on arXiv. Formal methods, security, and memory for AI agent systems.
→ Biologically-inspired forgetting, cognitive quantization, multi-channel retrieval
Read on arXiv →→ 1,980 experiment sessions across 7 models
Read on arXiv →→ 675 tests, 8 novel contributions
Read on arXiv →→ 74.8% on LoCoMo (zero cloud) — highest local-first score reported
Read on arXiv →→ Local-first architecture, Bayesian trust defense against memory poisoning
Read on arXiv →→ Stochastic testing across non-deterministic agent workflows
Read on arXiv →→ Universal Type-C port for AI agents — 25 commands, every transport, every IDE
Read on arXiv →Google's Project Jitro (Jules V2) is building a persistent agentic workspace with goals, insights, and history. This is exactly the problem SuperLocalMemory solved — locally, privately, and months earlier.
Block's security team ran a red team exercise against their own AI agent Goose and achieved full compromise. The findings reveal architectural vulnerabilities that affect every AI agent connecting to external tools via MCP.
The EU AI Act (Regulation 2024/1689) takes full effect August 2026. Most AI agent memory systems send data to cloud LLMs — creating compliance challenges that engineering alone cannot solve. Here is the architectural analysis.
"The signal is always there.
You just have to build the filter."
10 tools in the Qualixar suite. New releases every 2 weeks.
Follow the research, the code, and the experiments.
