I bridge the gap between cutting-edge Generative AI and strict enterprise cloud security. With 19+ years of back-end engineering experience across highly regulated sectors (cloud, healthcare, fintech), I specialize in architecting infrastructure and agentic AI inference pipelines that allow enterprises to deploy AI securely, scalably, and cost-effectively. Right now, the industry is transitioning from building AI prototypes to deploying production-grade AI. My work focuses entirely on that intersection: building multi-agent systems and RAG pipelines that adhere strictly to AWS enterprise governance, SOC 2, HIPAA, and regional frameworks (PCI-DSS, CBUAE, QCB), while optimizing the underlying inference engines for production workloads. Recent Engineering Highlights: 🔒 Securing the Cloud: Architected an enterprise multi-region AWS security scanner and CSPM/CNAPP platform for complex customer environments. 💰 Cost-Optimized AI Inference: Engineered hybrid inference architectures routing between AWS Bedrock (Claude) and local Ollama models, successfully driving down API inference costs by 70% while maintaining strict data residency. 🤖 Agentic AI & Inference Engineering: Developed production-grade multi-agent reasoning loops (LangGraph, MCP) and optimized their inference pipelines for low-latency, high-throughput execution, automating natural-language compliance audits over Terraform state and AWS Config. 🔮 Predictive Security: Built predictive ML modules (Isolation Forest, LSTM) to forecast infrastructure drift and IAM misconfigurations 24-72 hours ahead of incidents. What I Can Help You With (Note: These will be the "Topics" or "Call Types" you set up on Topmate) 1. Agentic AI Inference Engineering & Optimization Agents require multiple, compounding LLM calls. I can help you architect inference pipelines for multi-agent systems (LangGraph, MCP) to minimize latency, maximize throughput, manage context windows, and prevent runaway API costs in production. 2. Enterprise GenAI Architecture & Security Moving your AI from a risky prototype to a secure reality. Designing RAG pipelines and agentic workflows that comply with SOC2, HIPAA, and regional data residency laws without bottlenecking performance. 3. Hybrid Inference & Cloud Cost Reduction Learn how to slash your LLM inference costs (I recently cut them by 70%) by architecting smart routing between managed services (AWS Bedrock) and local/open-source models (Ollama/vLLM) while maintaining strict security and data residency. 4. Cloud Security & Compliance Automation Architecting CSPM/CNAPP platforms, implementing FIPS-aligned AWS architectures, and using Agentic AI to automate compliance audits and predict infrastructure drift. 5. Career Mentorship & Leadership Guidance for mid-to-senior backend/cloud engineers looking to transition into Principal Engineering, Staff/Principal Architect, or AI-focused leadership roles. Who Should Book a Call? Founders & CTOs looking to integrate Agentic AI into their products without breaking compliance or blowing up their inference/cloud bill. Engineering Leaders & Architects needing guidance on Agentic AI inference optimization, secure AWS AI deployments, and complex RAG pipelines. AI/ML Engineers struggling with agent latency, context management, or high API costs in multi-agent reasoning loops. Software Engineers looking to upskill at the intersection of Cloud Infrastructure, Security, and Applied AI. Core Technical Stack Cloud & Security: AWS Enterprise Architecture, CSPM/CNAPP, IAM, Terraform, ECS Fargate, EventBridge, FIPS-aligned Architecture. Agentic AI & Inference: LangGraph, MCP, Multi-Agent Reasoning Loops, LLM Inference Optimization, Hybrid Model Routing (Bedrock + Ollama), RAG, Prompt Engineering. Machine Learning: AWS Bedrock, SageMaker, Predictive ML (Isolation Forest, LSTM). Let’s Connect / Current Focus I am currently open to Senior Architecture, Principal Engineering, and Strategic Consulting roles. If you are building in the Singapore, Qatar, Cape Town, or the broader GCC/APAC regions and need leadership at the intersection of Agentic AI Inference, Cloud Infrastructure, and Security, let's chat! (Feel free to book a call below to discuss potential collaborations, consulting, or just to geek out over AI infrastructure).