Show HN: Replaybook, an Infrastructure Agent Evaluation Framework
https://github.com/ducks/replaybook
I've been building Replaybook as an incident replay trainer. Recently, I started using it as an evaluation framework for infrastructure agents.
ducks_
Re:Ask HN: Who wants to be hired? (September 2026)
on Wednesday September 09, 2026 @11:45AM (#49628451)
Location: US
Remote: Yes
Willing to relocate: For the right opportunity
Technologies: Rust, Ruby/Rails, Python, TypeScript/JavaScript, PostgreSQL, Redis, Docker, Kubernetes, AWS, Terraform, NixOS, LLM infrastructure, agent runtimes, and evaluations
Résumé/CV: https://jakegoldsborough.com/resume/
Email: [email protected]
Re:Ask HN: Who wants to be hired? (August 2026)
on Wednesday August 12, 2026 @12:46PM (#49275255)
Location: Portland, OR, USA
Remote: Yes
Willing to relocate: Yes, to Czechia / EU
Technologies: Rust, Ruby, TypeScript/Node.js, Python, Kubernetes, Terraform, Docker, Nix/NixOS, AWS, GCP, PostgreSQL, Redis
Résumé/CV: https://jakegoldsborough.com/resume/
Email: [email protected]
Software engineer with 10+ years of experience.
I work mostly at the intersection of infrastructure, developer tooling, automation, and systems software. Recent production work includes building a Rust routing proxy for LLM inference, Kubernetes and Terraform infrastructure, CI/CD optimization, large-scale storage deduplication, and performance work across Ruby, SQL, Redis, and Docker.
Outside of work I build and write extensively about open-source developer tools, infrastructure experiments, LLM/agent orchestration, and evaluating agents in real running systems:
https://jakegoldsborough.com https://github.com/squirrelcanoe
I'm particularly interested in infrastructure/platform engineering, developer tooling, systems engineering, and AI/agent infrastructure roles. I like building tools, removing operational friction, and working on the systems around the software.
Strong preference for companies able to support relocation to Czechia or elsewhere in the EU, but open to compelling remote roles.
Show HN: Lok – Treating LLMs more like infrastructure, not chatbots
Hi HN,I've been building a small open-source CLI called Lok for orchestrating multiple LLMs in a single workflow.Instead of a single "agent", Lok treats models as interchangeable tools: one can plan, another can execute or critique, and others can verify output. The focus is on inspectable, composable workflows rather than autonomous behavior.It's local-first, CLI-driven, and intentionally...