AI / ML Platform
Model lifecycle, progressive delivery, delayed quality feedback, policy-driven release control and observable production operations.
Resume overview
Ömer Faruk Koç
MLOps & AI Platform Engineer — 3+ years building and operating production ML, data and GenAI systems, with current work focused on agent reliability, evaluation, observability and platform control.
View as MarkdownExperience
MLOps & Analytics Engineer
Fibabanka · Analytics Center of Excellence
Built and operated production ML, data and Generative AI platform capabilities across analytics workloads.
- Call-Center Intelligence~9,000 recordings / day
- ML Platform10+ production ML models
- Data Platform120 → 30 min
- Feature PlatformOne definition per feature
Featured project
Agentic Customer Service Platform
AI Reliability / Execution Infrastructure
Customer-service agent platform where the LLM proposes refunds, cancellations, lookups, tickets and escalations while deterministic software owns scope, policy, confirmation, revalidation, idempotency and execution.
D2c semantic safety validation
540/540 measured attempts
semantic/safety · semantic_decision_v3
30 unsafe semantic proposals, 30 deterministic guard interventions, 0 executable survivors, 0 executions. Also recorded: 0 confirmation bypasses, 0 unauthorized mutations, 0 duplicate mutations, 0 hallucinated identifiers. Evidence for this exact source, prompt, model, provider and contract binding — not a universal guarantee about future hosted-model behavior.
Core domains
Engineering areas
Generative AI / RAG
Retrieval, reranking, citation integrity, evaluation and private open-source model serving.
Distributed Systems
Event processing with explicit delivery guarantees, failure handling and measured service limits.
Data Engineering
Batch and near-real-time pipelines, transformation systems, quality controls and data lineage.
Agent Systems / Agent Infrastructure
Stateful agent workflows with deterministic control boundaries, confirmation and recovery, secure tool interfaces, evaluation and observability.