Senior AI Systems Engineer - Evaluation & Reliability

ExpertsHub.ai; San Francisco (CA); Vor Ort; USD 250.000 - 360.000; Vollzeit

Benefits dieser Stelle

Equity

Medical Insurance

Dental Insurance

Vision Insurance

401(k)

Work-From-Home Stipend

Commuter Transit Benefits

Zusammenfassung

ExpertsHub.ai is seeking an experienced backend engineering leader to own the strategy and infrastructure for evaluating autonomous agents and improving agent accuracy. You will build resilient backend systems for agent execution and evaluation, advancing platform quality and safety.

You will mentor engineers on evaluation and testing standards and drive end-to-end ownership of production AI products in a distributed, high-throughput environment.

Qualifikationen

• 6–15+ years of software engineering experience building production backend systems and AI-enabled software.
• End-to-end ownership of production AI products with distributed-systems expertise.
• Analytical approach to evaluations, error analysis, and resolving agent failures.

Aufgaben

• Own the strategy and infrastructure for evaluating autonomous agents and improving agent accuracy.
• Build resilient backend systems for agent execution and evaluation.
• Mentor engineers on evaluation, testing standards, and reliability practices.

Kenntnisse

Backend Systems Engineering

Distributed Architectures

AI Product Development

Autonomous AI Agents

Agent Knowledge Representations

Evaluation Strategy

Error Analysis

Reliability Engineering

Evaluation Pipelines

High-Throughput Systems

Dynamic Tool Calling

Real-Time Observability

Testing Practices

Mentorship

Technical Ownership

Jobbeschreibung

ExpertsHub.ai is seeking an experienced backend engineering leader to own the strategy and infrastructure for evaluating autonomous agents and improving agent accuracy. You will build resilient backend systems for agent execution and evaluation, advancing platform quality and safety.

You will mentor engineers on evaluation and testing standards and drive end-to-end ownership of production AI products in a distributed, high-throughput environment.