Senior LLM Agent Systems Engineer

Alex Ibarra is a Senior LLM Agent Systems Engineer with a decade of experience in production distributed systems, including roles at Uber, DoorDash, and Jobscan. For the past year, Alex has focused on designing and shipping autonomous, LLM-driven infrastructure. He is seeking a hands-on senior IC role on an AI-infra, agent-platform, or applied-AI team.

Key achievements include:
* At Uber, working on Cadence (open-source workflow engine, 12B+ workflows/month), executing multi-region failovers, shipping non-determinism detection, rebuilding cadenceworkflow.io, and onboarding 50+ teams.
* At DoorDash, developing a refund rules engine for McDonald's/Chipotle (500K refunds/month).
* At Jobscan, serving as Interim Head of Eng, achieving 97%

99.99% uptime through an AWS migration and recovering $475K/yr via payment A/B testing.
* Operating durable-execution systems at scale and developing strong opinions on the application of autonomous agents.

Recent projects (past year) include:
* Maquina: A structured "cognitive language" and control plane for coordinating heterogeneous LLM agents, featuring an EBNF grammar, evaluation harness, and a runtime for first-class multi-agent coordination.
* Meridian: A 29k-line TypeScript autonomous goal-graph executor (Postgres + MCP) that decomposes high-level charters into plan nodes and runs LLM-backed agents with a live dashboard, budget circuit-breakers, and governance enforcement.
* Pursuit (co-founder, AI Scalathon Seattle 2026): An agent-to-agent recruiting system that conducts 3-minute structured interviews to produce ranked multi-dimensional match scores.
* ApplyPilot (OSS): A multi-provider LLM orchestration system with cost-aware routing across Gemini/OpenAI/Anthropic, and Claude Code + Playwright automation across 40+ ATS workflows.
* OpenAI Parameter Golf: Contributed 14+ PRs to an LLM-training challenge, demonstrating hands-on experience with Int5/6 GPTQ, score-first test-time training, Triton kernels, and Hessian-based calibration.

Alex is looking for a team focused on hard problems in agents, evals, and inference, with a culture of daily shipping.