Iaroslav Kuznetsov

About

Built and scaled an internal AI code-search/assistant agent that expanded from engineering-only to broader internal users, tackling legacy code and inconsistent standards to make a RAG pipeline production-ready. Uses a metrics-driven approach (user feedback + automated Python evaluation for retrieval relevance and latency) and has handled high-pressure outages, including moving parts of the stack off AWS and adopting Milvus on internal infrastructure for resilience.

Experience

Key Strengths

• Took an internal LLM/RAG agent from prototype (Docker API) to production with scalable architecture and iterative rollout
• Improved RAG performance by addressing inconsistent coding standards and legacy code via refactoring and abstraction layers
• Established success measurement using user feedback loops plus automated retrieval/context relevance/latency testing
• Effective real-time incident diagnosis using tooling to trace prompts/flows/errors; identified AWS outage root cause
• Drove reliability improvements by migrating parts of stack off AWS and adopting Milvus on internal servers
• Tailors technical demos/workshops to audience; led internal workshop on RAG and MCP with strong Q&A

Reference Highlights

• Integral team contributor
• Strong in direct customer interactions
• Effective first line of support
• Simplifies complex technical concepts for customers
• Quickly becomes a domain expert across areas
• Creates reusable documentation and code used across the organization
• Incredibly gifted communicator in AI/ML
• Thrives in fast-moving and ambiguous environments
• High ownership; self-led projects
• Trusted by manager/reference
• Versatile; recommended for any job