Ömer Faruk Koç

MLOps & AI Platform Engineer

Building production AI/ML platforms, agentic systems, retrieval infrastructure and reliable data systems.

3+ years building and operating production ML, data and GenAI systems, with current work focused on agent reliability, evaluation, observability and platform control.

Explore projects Engineering graph GitHub

Türkiye · Open to remote opportunities · MLOps · AI Platform · GenAI

Request lifecycle

Request
AI Platform API
Agent Runtime
RAG Retrieval
Model Serving
Guardrail
allow
confirm
human
deny
Response

Trace + Metrics

Career highlights

At a glance.

Experience3+ YEARS: Production AI/MLProfessional experience across ML, data and GenAI systems.
Lifecycle10+ ML MODELS: Deployed & operatedProduction ML lifecycle ownership across multiple analytics use cases.
Scale~9M CUSTOMERS: Customer-level tablesBatch and near-real-time pipelines consolidating many source tables into customer-level training, inference and analytics tables.
Performance75% RUNTIME REDUCTION: Core ETL workflowSequential Oracle ETL re-architected with modular parallel dbt: 120 → 30 min.

Selected work

Systems, not demos.

Public engineering projects built around control boundaries, reliability, evaluation, observability and explicit trade-offs.

All projects

Project / 01current

AI Reliability / Execution Infrastructure

Agentic Customer Service Platform

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.

Execution authority

SERVER-OWNED

LLM proposal → deterministic execution

Authentication, scope, policy, confirmation, revalidation, idempotency and business execution stay outside the model. The exercised D2c slice recorded 0 unauthorized mutations and 0 unsafe executions.

View case study GitHub

Project / 02current

MLOps / AI Platform

ModelOps Control Plane

Policy-driven ML release control plane combining progressive canary delivery, delayed-ground-truth quality gates, automated promotion and rollback, and desired-vs-observed routing reconciliation.

Routing control loop

DESIRED ↔ OBSERVED

Durable database state → router reconciliation

The database owns desired traffic; the router is restart-losable observed state. A worker-triggered reconcile tick repairs drift after a restart or failed push.

View case study GitHub

Project / 03current

Generative AI / RAG Platform

Knowledge Base RAG

Local-first multilingual RAG platform with tenant-scoped hybrid retrieval, measured reranking, strict answer validation, versioned index operations and an evidence-first React console.

Multilingual reranker decision

63 rescues · 0 drops

220-query paired evaluation

BAAI/bge-reranker-v2-m3 reached cross-lingual Recall@5 1.0000 and MRR 0.9558 on the committed evaluation set. This result belongs to that dataset, model and runtime configuration.

View case study GitHub

Project / 04current

Distributed Systems / Streaming

Real-Time Commerce Platform

Production-oriented event-driven commerce platform where Kafka may redeliver, but layered idempotency, transactional persistence and bounded failure handling protect durable business effects.

Sustainable capacity improvement

750 → 1,050 evt/s (+40%)

Isolated local benchmark · Kafka → processor → persistence

Three processor workers matched to three Kafka partitions (750–775 evt/s was the original non-sustainable transition). Bounded per-partition offset-commit batching moved the sustainable boundary to ~900 evt/s; query-plan-driven PostgreSQL indexing plus a fresh capacity sweep moved it to ~1,050 evt/s, with ~1,075 evt/s the first repeatably degraded rate. Not production capacity or Demo Control throughput.

View case study GitHub

Engineering areas

Platform work across five connected domains.

Capabilities are grouped by engineering evidence—not percentages or keyword counts.

AI / ML Platform

Model lifecycle, progressive delivery, delayed quality feedback, policy-driven release control and observable production operations.

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.

Professional experience

Production systems at scale.

Fibabanka · Analytics Center of Excellence

MLOps & Analytics Engineer

Built and operated production ML, data and Generative AI platform capabilities across analytics workloads.

Period: Mar 2023 — Mar 2026
Location: Istanbul, Türkiye

Professional experience informs the engineering questions explored in public projects; the public repositories are independent work.

Explore experience

Current direction

Extending the platform boundary.

Planned and learning items are intentionally distinct from current, evidence-backed work.

Context Engineering for RAG

learning

Systematic selection, ordering and budgeting of retrieved evidence before generation.

AI Platform Observability

learning

AI-specific signals and explicit SLIs across model serving, retrieval and agent execution.

AI Platform on Kubernetes

planned

Moving model serving and rollout control onto orchestrated, resource-isolated infrastructure.

Open learning roadmap

Engineering graph

See how the work connects.

261 source-grounded nodes and 341 validated relationships across experience, projects, technologies, concepts, evidence and current learning directions.

Explore Engineering Graph

Contact

Have an interesting platform, data or AI infrastructure problem?

Open to remote opportunities · UTC+3 / Istanbul

Available for new opportunities

Email LinkedIn GitHub