Senior AI Ops Engineer, Application

What you'll do

• Build and operate high-throughput ingestion and feature pipelines for application logs, traces, and transaction events.
• Train, validate, and tune anomaly-detection and forecasting models using application and transaction-level signals.
• Develop LLM-based components for log parsing, summarization, and root-cause hypothesis generation with hallucination risk management.
• Design event correlation and probable-cause ranking logic to reduce raw application alert volume.
• Write, test, and version remediation automation for application-layer failures with tested rollback and kill-switch frameworks.
• Instrument and monitor production models and automations while participating in the on-call rotation for live actions.

What we're looking for

• Must have a Bachelor's degree or 4 years of relevant education and/or experience.
• Must have 5+ years of hands-on software or data engineering experience.
• Must have strong programming ability in Python plus a second production language.
• Must have practical experience productionizing ML models using frameworks such as TensorFlow, PyTorch, or scikit-learn.
• Must have working fluency with LLM-based techniques including prompt design and retrieval-augmented generation.
• Must have experience writing and testing operational automation including workflow orchestration and rollback design.
• Must be comfortable operating in a regulated environment and debugging live production incidents under pressure.
• US military experience gained through service or as a military spouse/domestic partner (preferred).