Open to opportunities

Kirill Zemskov

@kzemskov

Engineering Leader | AI Ops, Platform Engineering, Distributed Systems | RAG, Multi-Model Orchestration | Ex-JPM, Nasdaq

United States

Message

What I'm looking for

I’m looking for a role where I can lead backend platform delivery and reliability—pairing strong engineering governance with psychological safety—and apply AI/LLM tooling to improve ops, observability, and incident performance in mission-critical systems.

With over a decade of experience, I specialize in platform engineering and site reliability engineering (SRE) for distributed systems. At JPMorgan Chase, I focus on building and maintaining tier-0 last-mile regulatory reporting systems, ensuring data reliability, lineage, and audit-grade outputs. My work empowers global users with scalable self-service platforms and robust observability capabilities, leveraging tools like Kubernetes, Grafana and Splunk. Since 2024, I have contributed to the development and global adoption of internal AI/LLM operations, applying innovative solutions such as retrieval-augmented generation (RAG) for runbook queries, incident summaries, and structured change analysis. I am committed to fostering operational excellence, delivering deterministic and resilient systems that meet the highest standards of regulatory compliance and trust.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Engineer

Current

JPMorgan Chase

Jul 2024 - Present (1 year 11 months)

Served as tech lead and SME for multiple platform areas, owning end-to-end delivery and mentoring engineers through onboarding. Architected and shipped a self-service regulatory reporting platform for thousands of users and scaled AI/LLM-powered ops tooling adopted globally.

Java Python SQL Kubernetes Kafka Distributed Systems RAG OAUTH2

Head of Engineering

Nasdaq

Jan 2021 - Apr 2024 (3 years 3 months)

Led a 20-engineer organization for high-stakes regulatory reporting, defining team structure, SLOs, escalation policies, and release governance for 24/7 operations. Transformed incident response by reducing P0 MTTR from 50 minutes to 8 minutes and modernized observability with OpenTelemetry, Prometheus/Grafana, and ELK/Splunk.

Engineering Leadership Incident Command OpenTelemetry Prometheus Grafana ELK RAG

Vice President, Engineering

Nasdaq

Jan 2017 - Jan 2021 (4 years)

Owned end-to-end delivery for key Americas regulatory reporting platform initiatives, driving roadmap execution and cross-functional alignment with Product, Sales, and Client Services. Scaled and mentored engineering leaders and led multi-million-dollar technical PoCs integrating SAS Kamakura, IBM Netezza, Amazon Redshift, and Snowflake.

Performance Engineering Power Automate Python Data Warehousing POC

Regional Head of Technical Support

Nasdaq AxiomSL

Oct 2013 - Dec 2016 (3 years 2 months)

Led a regional enterprise SaaS technical support organization, setting escalation policies and coaching senior engineers. Improved product outcomes by converting repeat issues into prioritized defects, hotfixes, and monitoring enhancements, and managed crisis communications to protect platform trust.

Escalation Management Coaching Monitoring

Tier 2 Support Engineer

Veeam Software

Sep 2012 - Oct 2013 (1 year 1 month)

Owned tier-2 escalations for VMware vSphere, performing end-to-end debugging across virtualization, storage, and networking layers. Mentored new engineers and delivered cross-functional training to improve escalation quality and resolution speed.

VMware VSphere Troubleshooting Virtualization Storage Networking Technical Mentoring Functional Training Escalations