Julian Ortega

Staff Engineer

• Laying the foundation for an agentic system where LLMs plan, query, refine, and reason over internal search and merchandising engines via tool calls and API integrations
• Designed and built a working PoC of the Kubernetes migration for a core service of 500+ servers, using event-driven orchestration with zero downtime or upstream changes
• Owns the integration and orchestration layers connecting LLMs, internal APIs, and data pipelines

Staff Engineer

• Evolved a conversational agent from research to production with a single-agent-with-tools architecture at 20x lower LLM cost than the initial vendor; the pattern was later validated as the approach adopted by leading AI providers
• Built the tool-calling integration layer (MCP) exposing internal search and merchandising engines to the agent over APIs
• Built AI knowledge assistants that automated document processing and data extraction, crawling, transforming, and embedding ~900 documents and anonymized tickets; targeted ~18% of all support ticket volume with ~80% coverage validated and a 30% deflection target
• Shipped the evaluation harness as its own workstream before the feature, instrumenting accuracy and coverage
• Led architectural redesign of the suggestion ranking system, reducing index processing times by 64-93% and improving relevance by 15-18% in customer testing
• Owned service lifecycle end-to-end: deployment, monitoring, CI/CD, and cross-functional delivery

Software Architect

• Piloted AI coding assistants with an initial cohort of 15 engineers and ran the enablement, an early adoption of AI developer tooling across teams
• Evaluated and implemented an Internal Developer Platform for systems cataloging, ownership tracking, and developer self-service, integrating with internal tools
• Architected and shipped AI-powered semantic search adopted by enterprise retailers across fashion, sports, grocery, and DIY, supporting 40+ languages
• Drove CI/CD optimization delivering a 3x build speedup at lower infrastructure cost across the engineering organization
• Built serving infrastructure handling 100x traffic spikes (5K to 500K rpm) through autoscaling validated in production incidents

Team Leader / Line Manager

• Designed and shipped the Adaptive Personalization Engine from PoC to production, a microservices architecture with 6 core components processing real-time event streams at 200+ events/second across 4 major releases
• Built event-driven pipelines on Apache Storm and Kafka for real-time profile building and re-ranking, holding search response impact under 50ms average
• Initiated and led the search modernization project, reducing reindex times from 2+ hours to 26 minutes and achieving 99.8% of queries under 200ms
• Mentored junior developers, with 70% of team members receiving promotions during tenure

Senior Software Engineer

• Created a real-time recommendations engine proof of concept, integrating it into the core product
• Optimized product catalog ETL for 32M+ product catalogues, reducing reindexing time from 40 hours to 4 hours

Software Engineer / R&D Intern

• Developed search and recommendation algorithms processing terabytes of e-commerce data
• Automated and industrialized the evaluation process of recommendations, creating frameworks still used in production systems

Conversational Agent (Single-Agent-with-Tools)

• Self-initiated from research through PoC to production, with a narrative and live demo that supported prospect engagement
• Evolved architecture from modular intent routing to a single-agent-with-tools pattern with templated prompts and tone adaptation
• Evaluated LLM providers and reached a 20x lower cost than the initial vendor, with gains in intelligence, tool use, and speed
• Built the MCP tool-calling integration exposing internal search and merchandising engines to the agent over APIs

AI Knowledge Automation (Document Processing + RAG)

• Automated the largest addressable support category (~18% of all ticket volume), reducing resolution friction for common questions
• Internal trial validated ~80% documentation coverage for real questions
• Designed for measurable deflection with a 30% reduction target, against average resolution times of 20+ days
• Processed and embedded ~900 knowledge base pages and anonymized tickets into the retrieval pipeline

Internal Developer Platform & AI Coding Assistant Rollout

• Piloted AI coding assistants with an initial cohort of 15 engineers and ran the rollout and enablement
• Evaluated and implemented an Internal Developer Platform for systems cataloging, ownership tracking, and self-service, integrating with internal tools
• Drove code quality analysis adoption across 5 heterogeneous product lines covering 2M+ lines of code
• Curated a 45-book professional development index and ran a supporting community channel to grow the team

Search Infrastructure Modernization (Event-Driven, Auto-Scaling)

• Evaluated 3 architectural options and recommended an event-driven approach requiring zero changes to existing ETL or orchestration
• Built a working PoC demonstrated at the cross-team kickoff with positive reception
• Designed event-driven distribution and cache persistence preserving performance across restarts and scaling events

Master's in Computer Science (AI Specialization)

B.S. in Systems Engineering