Eidetic

AI product and systems engineer · London

Portrait of Robin Miklinski.

Robin Miklinski

Fifteen years making software dependable. Now I do the same for AI.

From defence intelligence to SaaS used by millions. I build AI products, test their limits and improve the systems behind them.

Discuss a project → See selected achievements ↓

Taking on contract work. Open to the right permanent role.

Previously

  • Reward Gateway Employee engagement platform
  • ASOS Global online fashion retailer
  • Perkbox Employee benefits and wellbeing platform
  • Huddle Secure document collaboration platform
  • BAE Systems Detica Cybersecurity and intelligence consultancy
  • Steria Defence UK Defence technology consultancy
  • HP Computing and printing technology
  • Fujitsu Digital services and IT systems

Selected results 01—03

Evidencing AI Quality Reward Gateway · Employment history
Built automated tests to challenge prompt-injection defences, check tenant isolation and verify personal data protection across web, iOS and Android.
Growing an engineering team whilst rebuilding its delivery infrastructure Reward Gateway · Employment history
Built and led a team that grew from 4 to 15 engineers, supporting more than 200 people across product and engineering.
Rebuilding an inherited planning applications scoring system Your Right 2 Light · Client engagement
I re-architected a large planning application database, restoring council datasets and rebuilding the scoring system.
01 / Achievements

Selected achievements

career/ops Independent product

career/ops: building a system for career research and outreach

  • Product engineering. I designed and built a private career workspace from scratch, covering the interface, data model, research workflows and deployment.
  • Research and integration. Job alerts and public sources feed scheduled collection and AI-assisted research, supporting evidence briefs and draft messages.
  • Operation and reliability. The hosted application is in active personal use, with automated tests, service monitoring and backups.

The application is private and not yet available for wider use.

Independent product Read the career/ops product overview →
Reward Gateway Employment history · 2019–2026

Reward Gateway: engineering systems at organisational scale

  • AI product evaluation. The company’s first customer-facing AI product was evaluated against reference answers, with automated regression checks.
  • Incident analysis. A Python pipeline analysed hundreds of production incidents over ninety days and supported a £227,000 annual business case for preventable failure.
  • Delivery infrastructure. I built and optimised the test pyramid running in CI, including automated functional and non-functional tests (pytest, Cypress, JMeter load tests).
Employment history Read the Reward Gateway case study →
Your Right 2 Light Client engagement · 2025–2026

Your Right 2 Light: rebuilding the systems behind planning decisions

  • Rebuilt the scoring system and integrated planning data in an inherited Dart, Flutter and Firebase application.
  • Delivered application notes and batch reassignment features, alongside tooling for production data corrections.
  • Restored a failed council dataset, recalculated planning application scores and onboarded the external development team.
Client engagement
02 / About

Background and experience

Engineering. Hands-on engineer and team leader. Former Head of Quality Engineering at Reward Gateway, building teams, evaluating AI products and preparing them for release.

  • Experience across defence, retail, collaboration software and global SaaS. From intelligence data systems to products used by millions.
  • Work is primarily in Python, JavaScript, TypeScript and C#. Qualifications include a BSc (Hons) in Internet Engineering from the University of Exeter.

Tools and technologies

Selected technologies across current product work and earlier platform delivery.

AI systems and agents
AWS Bedrock, OpenSearch, Ollama, Claude Code, Codex, MCP
Product engineering
Python, JavaScript, TypeScript, C#, SQL, React, Dart, Flutter, Firebase
Testing and assurance
pytest, Playwright, Cypress, Selenium, SpecFlow, Detox, Maestro, JMeter, Locust, k6, OWASP ZAP, axe, BrowserStack
Cloud and delivery
AWS, Azure, Cloudflare, Amazon SQS, Docker, Kubernetes, Terraform, GitHub Actions, GoCD, TeamCity, LaunchDarkly
Data and observability
SQLite, Redshift, Datadog, New Relic, Tableau, Heap
Workflow integrations
Jira, Confluence, Zapier

Speaking. A 2024 talk at BrowserStack in London, Observable Test Automation at Scale, covered scaling test automation and GenAI-assisted pull-request review.

Outside engineering. Electronic music production, audio engineering and DJing. Behind the decks at EGG London and on air with a show on AAJA Radio.

03 / Selected code

Tools from my music workflow

eidetic-sample-tools

Find, organise and prepare samples for music production. A Python toolkit bringing together local AI, audio analysis and hardware integration.

  • Local AI classification. Audio–text models classify samples, with cached embeddings and a listening interface for reviewing uncertain results. The classifier is experimental.
  • Audio search and curation. Search combines musical role, character and acoustic similarity with audition playlists and curated collections.
  • Hardware integration. Exports support Octatrack, Digitakt and TR-8S, with format and capacity checks. Content hashes verify sample identity; original audio is preserved.
Source →

audio-service

An audio-processing service for metadata cleaning, BPM detection and FLAC-to-AIFF conversion, with source retention enabled by default.

Source →
04 / Contact

Tell me about your project.