Lead Software Engineer, Agentic AI

What you'll do

• Build autonomous agent capabilities to plan, execute, and submit code changes in bulk for large-scale migrations and remediations.
• Integrate AI-driven remediation workflows into enterprise CI/CD pipelines with automated gating and audit evidence capture.
• Develop and operate evaluation harnesses to measure agent quality, success rates, and safety across various software domains.
• Implement end-to-end PR-provenance contracts including branch creation, signed commits, and automated verification gates.
• Manage subsystem components such as replay tooling, regression corpora, and failure triage for the evaluation harness.
• Ensure reliability and observability of agent systems through metrics, logging, tracing, and proactive alerting.
• Instrument performance and adoption metrics to quantify engineering time saved and audit evidence completeness.
• Drive team adoption of enterprise-authorized AI tools while establishing standards for secure coding and automated testing.

What we're looking for

• Formal training or certification in software engineering and 5+ years of experience developing, debugging, and maintaining code in a corporate environment.
• Experience contributing to CI/CD, DevOps, or release-engineering platforms including build automation, signed-attestation systems, and audit-trail tooling.
• Strong hands-on experience with Java, Spring Boot, Kafka, API development, Python, and Shell scripting for building automation services and test harnesses.
• Hands-on experience using enterprise-authorized AI-assisted software development tools to create code, tests, and documentation while validating outputs for security and performance.
• Understanding of responsible AI use in engineering workflows, including data sensitivity, secure input/output handling, and guiding peers on safe usage practices.
• Hands-on experience with AWS or Azure cloud platforms, Kubernetes, Docker, Helm, and various database systems within controlled enterprise environments.
• Experience operating end-to-end on subsystems including implementation, deployment, observability, alert response, and production support using tools like Prometheus or Grafana.
• Working understanding of Git internals, branching workflows, repository governance, and large-scale change orchestration.
• Formal training or certification in AI/ML engineering or cloud-native engineering (preferred).
• Proficiency with model-evaluation tooling or ML frameworks such as TensorFlow, PyTorch, or Scikit-learn (preferred).
• Experience automating infrastructure-as-code development using AI/ML-assisted workflows and tools like Terraform or Ansible (preferred).