Staff II Software Engineer, AI/ML Ops

What you'll do

• Build and maintain high-performance PySpark ETL pipelines to power AI-driven accounting agents.
• Establish robust data connections using APIs and tools like FiveTran, Plaid, and internal connectors.
• Architect and manage model registries and feature stores to support version tracking and reproducibility.
• Design and manage training infrastructure including distributed orchestration and GPU/TPU resource allocation.
• Build CI/CD pipelines to automate LLM agent deployment, policy validation, and prompt evaluation.
• Implement observability systems to track conversation outcomes, factual accuracy, latency, and safety events.
• Architect end-to-end guardrails for AI agents including prompt injection protection and tool authorization.
• Develop automation scripts and orchestration systems to streamline the end-to-end machine learning lifecycle.

What we're looking for

• Bachelor's or Master's degree in Computer Science, Machine Learning, Data Science, or a related field.
• Strong programming skills in languages such as Python, Java, or Scala.
• Expertise in ML frameworks (TensorFlow, PyTorch, scikit-learn) and orchestration tools (Airflow, Kubeflow, Vertex AI, MLflow).
• Proven experience operating production pipelines for ML and LLM-based systems across cloud ecosystems (GCP, AWS, Azure).
• Deep familiarity with LangChain, LangGraph, ADK or similar agentic system runtime management.
• Strong competencies in CI/CD, IaC, and DevSecOps pipelines integrating testing, compliance, and deployment automation.
• Hands-on experience with observability stacks (Prometheus, Grafana, Newrelic) for model and agent performance tracking.
• Proficiency in containerization technologies such as Docker and Kubernetes.