Senior Software Engineer - LLM‑Driven Release & Triage Tooling

Responsibilities

• Perform root cause analysis of events coming from on-road testing and simulation testing of an automated driving system.
• Partner with release engineers, triagers, and infrastructure teams to understand real-world failure modes, identify high-value automation opportunities, and iterate on models, heuristics, and tooling based on feedback and outcomes.
• Build and maintain tooling that uses AI/ML and LLMs to analyze test and release failures across logs, metrics, images, and video.
• Design systems that surface meaningful insights, root‑cause hypotheses, and confidence signals to engineers to support release decisions.
• Develop tooling that supports release qualification, gating, and readiness assessment, including large-scale simulation-based testing workflows.
• Integrate AI-based analysis into CI/CD systems, test frameworks, simulation platforms, and internal data pipelines to create seamless end-to-end workflows.
• Design and implement scalable, reliable internal services used by release and triage teams, ensuring maintainability, observability, and performance at scale.
• Build dashboards and reports that communicate release health, risk, and trends to stakeholders across Release, Triage, and development teams.
• Use AI-assisted coding tools to accelerate development, refactoring, and testing, while rigorously validating AI-generated code for correctness, security, performance, and maintainability.
• Help establish best practices for responsible and effective use of AI code generation and AI-driven analysis within the team.
• Write clear documentation and usage guidelines so internal users can effectively adopt and extend the tooling you build.

Requirements

• Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.
• 3+ years of professional software development experience (mid-level) or 5+ years (senior-level).
• Strong proficiency in at least one general-purpose programming language (e.g., Python, C++, Rust, Java, Go).
• Experience building internal tools, platforms, or infrastructure services used by other engineering or operations teams.
• Strong debugging and analytical skills, especially in complex, distributed, or data-intensive systems.
• Familiarity with CI/CD systems and release-adjacent workflows, including integration with test frameworks and data pipelines.
• Experience applying AI/ML or LLMs to real-world software systems, ideally in tooling or infrastructure contexts.
• Hands-on experience using AI-assisted code generation tools in a professional environment, including defining review practices.

Qualifications

• Familiarity with model evaluation, confidence scoring, and/or explainability techniques for AI-driven analysis.
• Experience with simulation-based testing, CI/CD, or release engineering workflows in safety-critical or high-reliability domains (e.g., automotive, robotics, aerospace, medical).
• Experience with triage tooling, incident review, and data visualization for operational dashboards.

Skills

• Experience with multimodal data (text, logs, structured data, images, video) and building systems that interpret complex signals.
• Experience with model evaluation, confidence scoring, and/or explainability techniques for AI-driven analysis.
• Experience with simulation-based testing, CI/CD, or release engineering workflows in safety-critical or high-reliability domains (e.g., automotive, robotics, aerospace, medical).
• Experience with triage tooling, incident review, and data visualization for operational dashboards.

Benefits

The base pay for this position ranges from $ 115,500 - $ 189,750 a year. Your base salary is one part of your total compensation. We offer a base salary, short term and long term incentives, and a comprehensive benefits package. The total compensation offered to an employee will be dependent upon the individual's skills, experience, qualifications, location, and level.