Hilary

HILARY AZIMOH
AI ENGINEER | LLM SYSTEMS • RAG • AGENTS • RESPONSIBLE AI GOVERNANCE

LinkedIn
Amsterdam,
📞 [відкрити контакти](див. вище в блоці «контактна інформація») ✉️ [відкрити контакти](див. вище в блоці «контактна інформація») A
Netherlands -
Portugal •
🔗 Github
​
Remote-friendly Portfolio

PROFILE
CORE SKILLS
AI Engineer specializing in building production-style AI systems using
large language models, Retrieval-Augmented Generation (RAG), and AI / ML
agent-based architectures. ●​ RAG, LLM grounding, hallucination
Focused on designing end-to-end systems that combine reasoning,
mitigation
retrieval, and automation into usable products.
Background in AI governance, cybersecurity, and platform engineering ●​ AI agents & agentic workflows
enables building systems that are reliable, explainable, and aligned ●​ Prompt engineering & structured
with real-world constraints (EU AI Act, NIST AI RMF). outputs
●​ Embeddings & semantic retrieval
EXPERIENCE
AI GOVERNANCE & SAFETY
AI Engineer / Founder — HC Core Tech
●​ EU AI Act, NIST AI RMF, OECD AI
Netherlands | 2025 – Present Principles
• Design and build applied AI systems including AI agents, RAG ●​ Explainable AI (XAI), model
pipelines, and automation workflows transparency
• Translate ambiguous requirements into structured AI system logic
●​ AI risk assessment & responsible AI
with predictable behavior
• Develop production-ready AI pipelines using FastAPI, embeddings,
and LLM reasoning BACKEND & SYSTEMS
• Apply Responsible AI principles including explainability, safe-failure ●​ FastAPI, REST APIs
design, and source attribution ●​ System architecture & design
• Deploy full-stack AI systems using Vercel (frontend) and Render ●​ Vector databases (FAISS, ChromaDB)
(backend)
FRONTEND
Data & AI Governance Manager (Contract) ●​ React, Next.js, TypeScript
Voice4AI Governance | Remote (USA) | Jan 2025 – Jan 2026 INFRASTRUCTURE
• Supported Responsible AI programs aligned with EU AI Act, NIST AI ●​ Docker, CI/CD concepts
RMF, OECD AI Principles, and ISO 42001 ●​ Vercel, Render, AWS/Azure (familiar)
• Contributed to AI risk assessments, model transparency
documentation, and accountability mapping SYSTEMS FOUNDATIONS
• Translated governance requirements into technical constraints and ●​ Cybersecurity, platform reliability
system-level controls with engineering teams ●​ Incident response & debugging
• Researched bias, explainability (XAI), and failure modes to inform
practical AI system design
• Bridged policy and engineering to enable responsible AI (See portfolio linked above.)
implementation
 AI ENGINEERING PROJECTS
AI Developer & Governance Lead (Contract) AI CAREER AUTOMATION AGENT
●​ Full-stack AI assistant (FastAPI +
Mediaverse | Remote (Singapore) | 2025 – Present Next.js) simulating recruiter interaction
• Designed modular AI systems using LangChain, LangGraph, and n8n workflows
Architected multi-layer AI systems (interface, orchestration, memory, ●​ Implements context-aware responses,
governance) tool usage, and conversion-driven
• Built agent workflows for multi-step reasoning, decision support, and design
automation GitHub:
• Implemented structured memory (SOPs, playbooks, constraints) https://github.com/Hillariaa/ai-automation-age
nt
using data-first architecture (file → vector)
AI KNOWLEDGE COPILOT (EXPLAINABLE
• Developed reusable frameworks for orchestrating agents, tools, and
RAG SYSTEM)
APIs ●​ Built explainable RAG pipeline using
• Integrated human-in-the-loop validation for controlled execution embeddings + vector search
• Documented systems and workflows to ensure traceability and ●​ Implemented grounded responses
non-technical reviewability with source attribution to reduce
• Worked in a structured lifecycle (plan, document, build, test, improve) hallucination
with continuous system learning GitHub:
https://github.com/Hillariaa/ai-knowledge-copi
Systems, Security & Platform Foundations (5+ years) lot
AI INTERVIEW INTELLIGENCE
Experience spanning technical support, cybersecurity, frontend
●​ Multimodal system combining
development, and operations across production and regulated speech-to-text and LLM reasoning
environments. ●​ Generates structured candidate
• Investigated API failures, authentication issues, and platform evaluation insights
incidents using logs and monitoring tools GitHub:
• Performed vulnerability analysis aligned with OWASP Top 10 and https://github.com/Hillariaa/ai-interview-intellig
simulated common exploits (SQLi, XSS) ence
• Conducted root cause analysis and documented remediation AI RESEARCH AGENT
strategies to improve system reliability ●​ Autonomous research system using
• Collaborated with engineering and security teams on incident LangGraph for multi-step reasoning
response and system debugging ●​ Produces structured outputs with
• Built frontend applications (React, TypeScript) with API integrations referenced insights
and responsive UI systems GitHub:
• Developed strong foundations in process discipline, documentation, https://github.com/Hillariaa/ai-research-agent
and escalation handling
• Gained practical understanding of how systems behave under failure, CERTIFICATIONS
load, and real user interaction
●​ Google Cybersecurity Professional
Certificate
●​ AWS Academy Graduate — Cloud
Foundations
EDUCATION ●​ IBM AI Engineering
BSc (Hons) Computer Science (in progress) — Open Institute of ●​ Responsive Web Design (SheCodes /
Technology (Remote) freeCodeCamp)
Sep 2024 – Dec 2026
Relevant coursework: Artificial Intelligence, Machine Learning, Data LANGUAGES
Science, Information Security English • Russian • French • Dutch