AI extraction accuracy, room-name matching
78.8%90.6%VERIFIED
18 fixtures · 773 ground-truth rows · production AI pipeline
ANITA LIPSKY
Anita Lipsky
AI ENGINEER
ABOUT
About
Anita Lipsky is an Australian AI engineer who builds production AI systems and proves their reliability through systematic ground-truth evaluation, drawing on fifteen years of software quality engineering.
WORK
What she does
Build production AI systems
GPT, Gemini, and Claude integrated into real production pipelines. Multimodal document and image extraction, agentic workflows. Not just prototypes.
Evaluate AI rigorously
Ground-truth datasets, regression evaluations, prompt and output testing, scenario-based behavioral testing, model telemetry and monitoring. Turns "I think it improved" into a measured number.
Build search and data systems
Elasticsearch architecture, relevance tuning, RAG and hybrid keyword/vector retrieval, indexing pipelines. At production scale, across large content bases.
Engineer full-stack
TypeScript, JavaScript, Python, Node.js, React, Next.js, REST APIs, CI/CD on GCP and Azure.
Own quality end to end
Automated test pipelines, API and end-to-end testing, security and performance testing. The practices that keep a system trustworthy as it changes.
CONTEXT
Context
Anita Lipsky is an Australian software engineer available for senior AI engineering roles and contracts.
Her work is focused on the production AI lifecycle: building AI features, running evaluations to prove they work at the required standard, and maintaining the evaluation infrastructure as models and requirements change over time.
She does not work in AI research or model training. Her domain is applied AI engineering: the work of integrating AI models into real systems and proving those systems are reliable.
WORKS AND CREDENTIALS
Works and credentials
Fantastic Elastic
A book on Elasticsearch and Kibana, published on Leanpub. Written for engineers working with search, indexing, and data pipelines at production scale.
ART of Testing
A methodology for AI evaluation: Asserts, Readability, Tested. Defined and applied by Anita Lipsky in production AI engineering work.
Evaluation-first AI engineering
An engineering discipline that treats AI output as a claim to be verified against ground truth before being trusted, building evaluation into the development loop rather than treating it as a post-hoc check.
Certifications
Elastic
- Elastic Certified Engineer · issued Nov 2019, expires Nov 2027 · ID 19484303
- Elastic Certified Analyst · issued Mar 2021, expires Mar 2027 · ID 30187874
- Elastic Certified Observability Engineer · issued Feb 2023, expires Feb 2027 · ID 776490
Microsoft
- Azure Fundamentals (AZ-900) · issued Mar 2020 · ID H387-3121
- Technology Associate: JavaScript Programming (MTA 98-382) · issued Apr 2020 · ID H411-3616
- Technology Associate: HTML and CSS (MTA 98-383) · issued Apr 2020 · ID H397-0702
- Azure Data Fundamentals (DP-900) · issued Nov 2022 · ID I487-3756
ISTQB
- Certified Tester Foundation Level · issued Aug 2016 · ID 16-CTFL-01616-NOR
- Agile Tester Foundation Extension · issued Mar 2018 · ID 18-CATE-01819-NOR
- Advanced Level Test Automation Engineer · issued Feb 2020 · ID 250924
VERIFIED RESULTS
Verified results
Sourced, measured results from production systems.
AI extraction accuracy, size matching
77.5%88.5%VERIFIED
18 fixtures · 773 ground-truth rows · same evaluation run
National library search platform
ZeroLive, 1M+ records searchableVERIFIED
Built from scratch · production in ~3 months · national institution
Global education platform, search and data quality
Hundreds of sites · dozens of languages · 300M+ pagesVERIFIED
Long-running engagement · production search infrastructure
Serialization platform, automated REST API testing
6B+ products supportedVERIFIED
Production platform · automated test pipeline
Test and release environment setup
Multiple developer-daysUnder one hourVERIFIED
Repeatable setup · automated pipeline · production engineering
Fortune 500 reporting tool, page load time
Multi-minuteUnder 3 secondsVERIFIED
Production web application · performance engineering
Foundstone security testing
Contributed to A ratingVERIFIED
External security audit · production system
Amazon Oslo GenAI Hackathon
3rd placeVERIFIED
November 2025 · agentic AI solution shipped in one day · newly formed team
Fantastic Elastic
PublishedVERIFIED
Free ebook · purplebugs.com/fantastic-elastic
RELATIONSHIPS
Relationships
| Relationship | Target |
|---|---|
| Founded | Purple Bugs AS |
| Authored | Fantastic Elastic |
| Operationalises | ART of Testing |
| Operationalises | Evaluation-first AI engineering |
Version 1.0 · First published: [launch date — fill at launch] · Last updated: [date]