Valentin Bonnet

San Francisco, CA  ·  github.com/vbonnet  ·  linkedin.com/in/valentinbonnet

Download resume (PDF)

Tech Lead with 12+ years building developer infrastructure at Google and Verily. Current focus: AI agent infrastructure — meta-harnesses, MCP tooling, context architecture, and testing frameworks that give non-deterministic LLM output measurable correctness guarantees. Active open source author in the AI agent engineering space.

Open Source

dear-agent — github.com/vbonnet/dear-agent

A pluggable meta-harness for autonomous AI coding agents, formed by merging two earlier projects (a harness layer and a memory/knowledge layer) into a single product.

  • Harness-agnostic adapter interface unifying Claude Code, Gemini CLI, Codex CLI, and OpenCode behind one session lifecycle. Copy-on-write workspace isolation (OverlayFS on Linux, APFS on macOS), state-aware async message routing, and advisory file reservations for safe parallel agent workflows.
  • DEAR protocol for research-loss prevention: enforces commit / push / human-readable branch / completion-notification gates before a session can be archived, eliminating the "stranded work on UUID branches" failure mode that plagues long-running agent sessions.
  • Persistent cue-based memory so agents retain context across conversations and sessions, with a metacontext Go service backing 3-tier (filter → rank → load) retrieval at <1ms p50.
  • Phased SDLC workflow engine (Wayfinder) with LLM-as-judge validation gates and a plugin architecture for MCP connectors and tool integrations. Go, Apache 2.0.

Technical writing

I write about AI agent engineering, developer tooling, and what breaks when agents try to be software engineers.

Read the series →

Skills

Go, Python, Java, C++, SQL. LLM integration, RAG pipelines, MCP (Model Context Protocol), multi-agent orchestration, non-deterministic testing, context window management, agent safety and correctness. Bazel, Kubernetes, distributed systems, CI/CD, developer platform engineering. gRPC, Protobuf, GCP, SQLite. IAM, identity providers, SCIM.

Work Experience

Senior Software Engineer / Tech Lead, Verily

Tech Lead, Developer Platform  ·  2024 – Present (parental leave through May 2026)

Verily is a precision health company under Alphabet (~1,000 engineers). Developer Platform owns the tooling, SDKs, and shared services the full engineering org builds on.

  • WIAM/DAG strategy: Set technical strategy for Workforce Identity Access Management (WIAM) and Data Access Governance (DAG) teams, supporting ~1,400 employees.
  • ViDA platform: Design partner for the Verily Developer Assistant (ViDA), an AI plugin providing AI agents secure access to internal content repositories via local MCP servers.
  • Agent evaluation harnesses: Designed test frameworks for non-deterministic LLM output at scale. Product teams can now ship agentic features with measurable correctness guarantees rather than relying on manual spot-checks, reducing post-launch rework cycles.
  • Cross-team technical leadership: Sets cross-team technical direction, reviews architecture proposals, and aligns with product and infra leads on roadmap priorities.

Tech Lead, Google — Core Infrastructure (Boq)

Nov 2021 – Aug 2024

Boq is Google's internal build and deployment platform, used by tens of thousands of engineers.

  • Set technical strategy for the Boq Conformance & Isolation team.
  • Designed, built, and maintained Bazel Rules powering 100K+ build targets.
  • Developed multi-quarter roadmaps to increase developer productivity and lower CI/CD costs across Google by catching errors earlier in the development loop.
  • On-call for high-QPS services critical to Google builds and service deployments.

Tech Lead, Google — YouTube Gaming

May 2018 – Nov 2021

  • Led migration of YouTube Gaming backends from the YouTube Python monolith into C++ microservices.
  • Improved release velocity from weekly to daily.
  • Worked with ML, Search & Discovery, and frontend teams to drive product alignment.

Software Engineer, Google — YouTube Paid Digital Goods

Jan 2016 – May 2018

  • Designed and launched backends for YouTube Live monetization features (Super Chat, Channel Memberships) — sub-second latency to millions of concurrent global requests.
  • Coordinated with global commerce, legal, and compliance teams to meet regulatory standards.

Software Engineer, Google — YouTube Live

Dec 2014 – Jan 2016

  • Developed PlayStation and third-party API integrations for Live Chat.

Junior Software Engineer, Google+

Jan 2013 – Dec 2014

  • Built a shared code registry framework adopted by all Google iOS apps.
  • Developed OAuth and SSO flows for Google+ and Hangouts mobile apps.

Education

McGill University — Montréal, QC
B.Sc. in Computer Science  ·  2009 – 2013