Senior Software Engineer
Core
Designing and building major components of an AI-first, agentic-first evaluation platform to turn quality questions into rigorous, reproducible evaluations that gate what ships.
Role type
Senior Software Engineer (AI Evaluation & Agentic Systems)
Builds
An evaluation platform where autonomous agents are first-class operators, delivering services, pipelines, and tooling with observability and guardrails.
Domain
Artificial Intelligence / Autonomous Agents / Evaluation Systems
Deliverable
production ML models | infrastructure
Required skills
Large-scale distributed systems, reliability engineering, AI-first or agentic systems, AI/ML evaluation and benchmarking, .Net, Java, JavaScript, Rust, Python
Preferred skills
Modernization of evaluation runtime, cost and latency optimization, mentoring engineers, on-call reliability management
Technologies
.Net, Java, JavaScript, Rust, Python
Responsibilities
Design and build major components of the evaluation platform; implement graceful degradation, intelligent retry, and dependency-aware gating; write and review extensible, maintainable code; mentor less-experienced engineers; act as DRI for a system that gates releases; stay current with agentic systems and AI evaluation patterns.
Seniority
Senior, hands-on IC
