A practical engineering framework for choosing between workflow and agent: criteria, architecture patterns, evals, security, cost, and rollout plan.
Igor Yakushev
about me ML Engineer. Search, Recommendations, LLM, MLOps
I build ML and GenAI systems. I write about architecture and system design - articles and case studies: patterns, anti-patterns, checklists
Posts
Articles
Here I share experience, thoughts, and practices of ML/AI systems. From architecture to observability.
A practical guide to shipping a support RAG agent with tool-calls: architecture contract, release gates, policy enforcement, observability, and FinOps.
A practical MLOps framework for model releases: which gates are mandatory before rollout, and how to keep quality, SLO, and cost under control.
Projects
Cases
Projects with tasks, architecture, and metrics.
Voice AI Operator for Call Center
On-prem voice AI operator handles 72% of calls without human in 0.96s with 58% cost reduction.
Client: NDA Domain: FinTech
Problem: 600 seats in contact center, 9 min wait, SLA penalties and new AI Act requirements, regulations outdated faster than operators can learn.
Solution: On-prem stack with streaming, model cascade, orchestration, and knowledge base. Safety rules and manual escalation.
ML Inference Latency and Cost Evaluation Platform
Internal tool for profiling latency, throughput, and $/req of models in production
Client: NDA Domain: E-commerce
RAG Assistant for Catalog
MVP chat search with deployment automation, experiments, and quality monitoring
Client: NDA Domain: E-commerce
About
About Me
I'm Igor Yakushev . I design ML solutions that handle traffic, save money, and don't break on Saturday night.
Started with marketing and business before moving to engineering. Now I'm responsible for search and recommendations in production with 10+ million requests per day.
My focus is systems that live under load, don't break, and don't require a hero.
«make AI boring again»
ML Engineer · System design · Product approach
Contact
Contact
Ready to discuss ML projects and implementations, I respond personally.
Igor Yakushev,
ML Engineer
about me My current time: --:-- Amsterdam
Senior/Staff ML Engineer. System design, ownership, high-traffic ML systems.
Fastest way
Write in Telegram