# Philip Stevens ## Headline Engineering leader. Systems architect. French and British software engineer based in Paris. ## Profile I lead architecture across large-scale systems and grow engineering teams that deliver ambitious products. I am a French and British citizen based in Paris, with more than fifteen years of experience. Technical leadership at the intersection of systems architecture, organisation-scale delivery and engineer growth — setting direction, creating leverage and keeping product outcomes in view. ## Practice areas ### Architecture at scale Setting technical direction for complex platforms and high-traffic systems, with clear boundaries and standards that let teams move independently. ### Teams that grow Growing engineering groups, developing staff engineers and building the structures and ownership that turn strong individuals into durable teams. ### Commercial judgement Connecting architecture and delivery to customer needs, risk and business outcomes — so technical investment earns its place. ### AI-native delivery Making coding agents useful in everyday engineering through reusable skills, evaluation, adoption and workflows that improve over time. ## AI practice **The model is not the product. The harness is.** Coding agents — Muse Code, Claude Code, Codex — have commoditised the model. What separates teams that ship with agents from teams that drown in them is everything around it: skills that encode how your team actually works, evals that catch breakage before users do, MCP harnesses that give agents real tools with real guardrails. I work both sides of this. Inside Meta I take the company's latest AI and turn it into reusable skills, measured evals and repeatable workflows that product, design and engineering teams genuinely adopt. Externally, I define how third-party developers bring AI to the Wearables platform: llms.txt, MCP servers, agent-ready documentation. Agents don't replace engineering judgment — they amplify the teams that have it. My work is making that amplification reliable: define what good looks like, measure it, gate on it. Keywords: Muse Code, Claude Code, Codex, MCP, llms.txt, Skills, Evals, Agent harnesses, Llama Stack. ## Career highlights - Led 18 engineers across three teams at Qonto, growing the group from four engineers. - Migrated 200,000 customers through Secure Customer Authentication in three months. - More than 15 years of software development experience. ## Experience ### Software Engineer — Meta **Dates:** June 2023 — Present **Location:** Paris, France Work at the cutting edge of using and improving AI coding agents to help product, design and engineering teams become more productive. Create and manage reusable skills across Muse Code, Claude Code and Codex. Established large-scale skill systems for projects and organisations, supported by agent-ready documentation, `llms.txt`, MCP and repeatable engineering workflows. Manage the performance and evaluation of these systems over time, using evidence from real-world use to improve reliability and impact. Led adoption efforts across product, design and engineering so teams use AI coding agents effectively in their daily work. Oversee architecture across projects in the Wearables Device Access Toolkit and Wearables Developer Center — Meta’s SDK and developer hub for third-party developers building hands-free experiences on Ray-Ban Meta, Oakley Meta and Meta Ray-Ban Display. Work across an organisation of around 50 engineers under three managers, alongside the director of engineering. The platform opens access to the camera, microphone, speaker and on-device display. Much of the work sits where AI meets wearables, with a particular focus on the edge. **Metrics:** around 50 engineers; three managers. ### Qonto **Dates:** March 2019 — June 2023 **Location:** Paris, France Roles: - Senior Staff Engineer — July 2022 to June 2023 - Senior Team Lead — January 2022 to July 2022 - Lead Ingénieur — August 2019 to January 2022 - Ingénieur — March 2019 to August 2019 Grew the engineering group focused on acquisition flows from four to eighteen engineers across three teams, pairing product delivery with the technical and organisational work needed to scale. Led the technical implementation of Secure Customer Authentication, migrating 200,000 customers in three months and reducing fraud. Played a key role in moving 150,000 customer accounts from a partner core-banking system onto Qonto’s own platform. Trained staff engineers, built shared Kafka libraries, and raised the bar for asynchronous worker reliability, observability and data pipelines across the organisation. **Metrics:** four to 18 engineers; three acquisition teams; 200,000 SCA migrations; 150,000 account migrations. ### Principal Engineer — carwow **Dates:** May 2018 — March 2019 **Location:** London, United Kingdom Ran a team of five developers alongside a product manager and designer, using lean development to balance long-term company goals with short, quick iterations. Designed a new car-data architecture that decoupled the Elm front end from the Rails back end, enabling parallel delivery and reuse across other product problems. Introduced Clojure for data collection, building adoption through individual engagement, a week-long spike and workshops for junior and senior developers. **Metric:** team of five developers. ### Senior Software Developer — uSwitch Ltd **Dates:** September 2015 — May 2018 **Location:** London, United Kingdom Developed a CQRS architecture for third-party data feeds and a front-end API using Clojure, PostgreSQL and Elasticsearch. Built the Boolean Tree Query API that powered search, filtering and sorting across uSwitch Mobiles pages and associated services. Built tracking pipelines into BigQuery and worked on the Rails client portal, while helping move the wider architecture into uSwitch’s internal Kubernetes cluster without downtime. ### Senior Software Developer — Retechnica **Dates:** September 2014 — August 2015 **Location:** London, United Kingdom Developed a Ruby service-oriented architecture spanning Rails, Sidekiq and Sinatra, with AngularJS interfaces and Elasticsearch-backed search. ### Software Engineer — Reevoo **Dates:** March 2013 — September 2014 **Location:** London, United Kingdom Improved production monitoring with New Relic, Logstash and Sensu, and built fuzzy-search systems using Elasticsearch and RabbitMQ. Rewrote the tracking pipeline in Node.js while contributing across AWS infrastructure, continuous deployment, technical planning and project delivery. ### Software Developer — Tauri-Tec Ltd **Dates:** October 2012 — March 2013 **Location:** London, United Kingdom Built payment-processing software in Python with PayPal and Braintree, alongside content-management systems using Pylons, Pyramid, PostgreSQL and MySQL. ### Research Assistant — BlueJ Project **Dates:** October 2009 — September 2012 **Location:** Canterbury, United Kingdom Developed the BlueJ and Greenfoot Java IDEs, and built websites for students and teachers in Ruby on Rails. Worked on visualisations of user activity and database research into mistakes made by novice programmers. ### System Development Engineer — Siemens AG **Dates:** August 2007 — July 2008 **Location:** Vienna, Austria Worked in the Agile development lifecycle of Gigaset WiMAX routers, focusing on testing and bug fixing, and designed a Java tool for testing multiple routers. ## Education - BSc Computer Science with Year in Industry, 2.1 — University of Kent, 2005–2009 - Oxted County, 1998–2005 ## Technology ### Data MySQL, PostgreSQL, Elasticsearch ### Languages and frameworks Rust, Go, Haskell, Kotlin, C++, Swift, PHP/Hack, Clojure, Ruby (Rails and Sinatra), Python (Pyramid and Pylons), Java, JavaScript (Vanilla, NodeJS and Angular) ### Infrastructure Apache, Nginx, Chef, Puppet, Terraform, AWS, Google Cloud, Kubernetes ## Spoken languages - English — Mother tongue - French — C1 - German — Elementary ## External links - LinkedIn: https://www.linkedin.com/in/philip-stevens-a0927432/ - Wearables Device Access Toolkit and Wearables Developer Center: https://wearables.developer.meta.com/