Lajos Moczar
Tech Polymath, Senior Agentic Engineer / Architect
Profile
Twenty-five+ years across the full IT stack — engineering, architecture, infrastructure, security, DevOps, and executive leadership — with the past three years applying that foundation to AI-assisted, agentic and dark factory development workflows.
I model complex systems in my head across multiple dimensions: technology options, architecture, development velocity, testing, DevOps, management, security, reliability, failover, customer needs and management goals.
I innately understand what makes software development fail: lightweight or sloppy specifications, abstract architectures and lack of accounting for failure modes. These problems are the same whether dealing with a human team or agents. I've seen AI make the exact same mistakes developers make. I'm successful because I know how to prevent these problems and build performant and durable systems.
As a founder, consultant and service provider, I've used LLMs and agent-based approaches to improve and evaluate client projects, and to build real-world production systems: a streaming service, API-enabled SaaS platforms, mobile apps, DeFi services, DevOps tooling, observability platforms and cross-platform GUI applications. My AI experience is grounded in many years of experience in library science, search technologies, Big Data and ML.
To each client I bring the combination of genuine technical depth, the leadership range to develop and manage people effectively, and the cross-functional instincts that come from decades of aligning technical decisions with business outcomes, technical realities and customer satisfaction.
Core Competencies
AI Engineering & Context Architecture
- 20+ year background in BigData/ML, semantic search, classification, clustering, recommenders and library science
- Specification precision — system prompts, rigorous specification practices, schemas, constraints, guardrails, validations, quality/security requirements to produce correct, consistent agent behavior — derived from decades of hands-on design, architecture & human team management
- RAG pipelines — embedding/chunking design, evaluation harnesses, and retrieval pipeline tuning (LanceDB, Cohere, Voyage, OpenAI, LangChain)
- Harness design & multi-agent/multi-machine decomposition — workflow topologies, orchestration, delegation boundaries, MCPs, browser automation (Claude Code, Codex, Python, NodeJS, C++, Rust)
- Testing, validation and acceptance — rigorous handling for happy paths, edge cases, degraded & failure modes, agent failure patterns, agent drift
- Dark factory principles — collaborative product specification, semi-autonomous design, fully autonomous agent builds, tests, bug fixes via automated PR handling
- AI cost and observability — hands-on cost tracking, latency profiling, and token spend management
- LLM routing and model selection (OpenAI, Anthropic, Cohere, Voyage, LLaMA, Mistral)
Engineering Fundamentals
- Strong software engineering foundations: OOP, scalable system design, data-based designs, API-based distributed systems
- Development — C/C++, Java, Python, Rust, TypeScript, React, Node.js
- Data — analysis, data design, database, SQL, Big Data, ML, Kafka, Redis, search technologies
- Architecture — enterprise, solution, cloud
- Infrastructure — IaC (Terraform, Ansible, Helm), CI/CD, GitHub/GitLab, Kubernetes & containerisation, observability, runbooks, guardrails
- Cloud — AWS, Azure, GCP, OpenStack
- Production operations — decades of expertise in automation, redundancy, failover, incident handling, root cause analysis across code, data, and systems, and the post-mortem culture that prevents recurrence
- Data fluency — structures, design, management, flows and intelligence; translating data into actionable, automated decisions
Enterprise & Leadership
- Technical leadership across roles — CTO, principal architect, engineering manager, and senior individual contributor across three decades
- Large-scale distributed systems, high-availability infrastructure, security and compliance by design
- Full-stack delivery ownership — architecture, reliability, cost, customer impact, and evolution simultaneously
- Business and technical alignment — sustained practice translating between commercial outcomes and technical decisions
Selected Work Experience
Senior Agentic Context Engineer / DevOps & AI Engineer
Product workstream — Artifix Solutions
- Agentic builds — semi- and fully-autonomous builds; multi-server streaming service, DeFi notary service (smart contract + SaaS), mobile apps, ebook generation pipeline — subagents, automated issue raising & handling, cross-agent reviews, custom skills (plan, design, build, test, review, post-mortem, doc), rigorous product, quality, security, deploy and test specs
- RAG pipelines for publishing house data, and another for observability data — embedding generation, vector storage, retrieval logic for assistant responses in live telemetry (via InfluxDB), log data ingestion
- Outcomes: completion in 95% of human coding time; cleaner codebases; reduction of AI coding errors by 30%
Technologies: Claude Code, Codex, Cowork, NodeJS, TypeScript, AWS, Azure, Rust, Python, C++, Java, NextJS, React, Llama, Mistral, PyTorch, Gitea
Consulting workstream — On-Demand DevOps
- Using Claude Code to develop one-click DevOps automations for multi-cloud, multi-region workload portability — up to 90% of coding time completed by AI
- Audit, review, debugging, and repair of vibe-based SaaS systems developed by external clients
Technologies: Claude, ChatGPT, AWS, Azure, Terraform, Ansible, GitHub, GitLab, Vercel, Netlify, Supabase, Kubernetes, Redis
Senior DevOps Engineer & Team Lead
- Designed and implemented global Azure architecture for a FinTech banking-compliance SaaS platform
- Implemented greenfield DevOps automation and tooling; developed testing tools for telephony/SIP infrastructure
- Provided technical strategy to leadership; trained and mentored development and operations teams; managed the DevOps team
- Prompt-driven development of DevOps-related IaC tooling
- Outcomes: fast, repeatable deploys with built-in release criteria; ISO 27001/SOC 2 compliant; MTTD < 10 min, MTTR < 60 min, MTTF > 6 months
Technologies: ChatGPT, Copilot, Azure, AWS, Kafka, Mongo, ES, Databricks, Azure DevOps, Terraform, Ansible, Asterisk
Senior DevOps Engineer
- Implemented rigorous DevOps practices, increased automation, revamped GitHub pipelines, Packer for custom image builds
- Built a CI/CD pipeline that PXE-booted a cluster of machines running custom images for cluster integration testing
- Outcomes: cut build times from 3–4 hours to under 1 hour
Technologies: GitHub, Packer, PXE, Python, Java
Senior Cloud Architect & Team Lead
- Led design and implementation of a global, multi-cloud self-service data platform for customers and internal teams, based on a customized Kubernetes
- Enabled a productized deployment model and efficient CI/CD processes for one-click deployments to a cloud and/or region of choice
- Developed tooling to improve financial visibility and support cloud usage billing to users
Technologies: AWS, Azure, OpenShift, Kubernetes, Jenkins, Helm, Kafka, Redis
Senior Systems Engineer
- Managed architecture & operations of a large global AWS estate — EC2, EMR/Spark, Databricks, Route53, Lambda, CloudFront, Splunk, Redis
- Improved operational stability, monitoring, dashboards, alerting and observability, achieving lower MTTD/MTTR
Senior Enterprise Architect / Management Consultant
- Delivered architecture for IaaS/PaaS services (NSX, vSphere/vCenter, PXE, ScaleIO, NetApp), redesigned the CI/CD pipeline approach (Jenkins), and led real-time monitoring framework design with cross-cloud visibility
- Led feasibility studios on OpenShift, AWS, Azure and OpenStack; performed risk assessments on technology fit within functional project areas
- Reorganized the Swisscom architecture team to reduce churn with development teams
- Introduced a mid-level design specification practice that became a Swisscom standard
- Advised senior management on product roadmap and market positioning
Lead Architect & Backend Developer
- Designed and built a Java-based backend platform for a music-related social media startup: a multi-layered engine with Big Data & ML technologies for programmatic detection of social and music trends
Technologies: Spring, AWS, Kafka, Storm, Cassandra, SolrCloud, Lucene, HBase, Hadoop, YARN
Senior Developer & Architect
- Revamped and improved a Big Data warehouse based on Hadoop and Hive for online radio station user and music data intelligence
- Designed a new corporate analytics data model and a more strategic approach to analytics within the context of business KPIs and goals
- Led development of a MapReduce, HBase and Storm-based approach for handling large volumes of user event information
CTO
- In charge of partner-facing engagements and technical solution development for customers
Technologies: Intershop, Hadoop, MapReduce, HDFS, Hive, Hama
CTO
- Product management oversight, development team leadership and technical alignment between customers, business and internal teams; hands-on backend development to fill knowledge gaps or deliver faster
- Hired and managed teams across two locations in Ireland
- Re-engineered a SaaS platform previously built by an offsite team to better meet business needs; worked with third-party providers to design and deploy a PCI-compliant, fully redundant hosting topology
Enterprise Architect, Senior Developer, Team Lead
- 2007–2008: Senior Java developer for BACS and SEPA services (Mule, Hibernate, Spring, Maven, WebLogic, Oracle, SafeStore)
- 2010–2011: Enterprise architect and team lead for SEPA (credit, debit, clearing) systems (J2EE, WLS, SCA4J)
- Designed and managed the development of a number of related products and services
- Served as a technical pre-sales consultant for potential bank clients
- Performed a technical evaluation for a potential acquisition by VocaLink
Owner, Consulting CTO
- Provided CTO services to two e-commerce startups: defining technology portfolios, architecting products, engaging providers, hiring staff and developing IT plans and budgets
- For an e-commerce client: prototyped a system for analysing e-commerce NLP search queries to understand the relationship between search results and purchase behaviour (Apache Mahout, Lucene, Solr)
- For a hosting provider (sMedia): developed a SaaS e-commerce solution (Java, Solr, Hadoop, Hive, MapReduce, HDFS, Hama)
- For a TV video solution provider (Digisoft): analysed and improved performance of Java server and client applications on cable set-top boxes (Glassfish, Spring, Hibernate, Skelmir JVM)