Full Job Description
We are seeking an experienced AI Troubleshooting and Remediation Engineer to transform how customer issues are diagnosed and resolved across embedded software, Linux-based platforms, SONiC systems, and Docker-based environments.
In this role, you will combine hands-on system debugging with the design of autonomous AI agents and conversational workflows - analyzing customer logs, retrieving relevant support knowledge, identifying root causes, and converting recurring troubleshooting patterns into reusable AI agents, diagnostic tools, and remediation playbooks that guide support engineers toward faster resolution.
What You'll Be Doing
• Build and maintain AI troubleshooting and remediation agents that analyze customer logs, Linux logs, SONiC logs, Docker container logs, embedded traces, telemetry, crash dumps, and debug artifacts - while also personally debugging complex customer issues involving embedded software, C++, Linux, SONiC, Docker containers, networking behavior, firmware, and platform integration.
• Design conversational AI workflows that guide support engineers through issue triage, log analysis, root-cause investigation, and corrective-action planning.
• Implement AI-assisted knowledge retrieval - using semantic search, embeddings, and vector databases - to connect customer symptoms and log signatures to prior support cases, known defects, GitHub references, documentation, and troubleshooting guides.
• Develop production-quality Python tools, diagnostic automation, and AI workflow integrations.
• Convert recurring customer issues into reusable AI workflows, remediation playbooks, and support automation, continuously improving quality by reviewing incorrect or low-confidence outputs, tuning prompts, improving retrieval sources, and capturing resolved cases as reusable knowledge.
• Work directly with customers and internal engineering teams to gather data, explain findings, validate corrective actions, and drive issues to closure.
What We're Looking For
Education:
Bachelor's degree in Computer Science, Computer Engineering, Software Engineering, Electrical Engineering or a related field
Experience:
Core Requirements:
• Practical experience building or applying AI-assisted troubleshooting, remediation, or conversational AI workflows, including hands-on use of large language models.
• Strong hands-on Python skills for building production-quality tools, log-analysis pipelines, and AI workflow integrations.
• Experience with AI/ML frameworks (TensorFlow, PyTorch, or similar) and knowledge-retrieval systems (semantic search, embeddings, vector databases).
• Strong log analysis and root-cause investigation skills, with hands-on debugging experience in embedded, Linux, SONiC, or Docker environments.
• Ability to validate AI-generated findings for accuracy and communicate technical findings clearly to customers and internal teams.
Nice-to-Have:
• Experience with LangChain, LangGraph, or similar AI agent-orchestration frameworks.
• Experience with AI observability, agent tracing, prompt evaluation, regression testing for AI workflows, or measuring AI recommendation quality
• Experience with optical communications, telecom equipment, data center infrastructure, transceivers, or related network/platform domain knowledge.
Perks You'll Love
• Flexible time off
• Health and wellness benefits (physical and mental)
• Tuition reimbursement and career growth support
• A workplace built for you: free gym, games room, prayer room
• Subsidized meals, free coffee/tea
• Employee stock options and incentive plans
• A collaborative, innovative, and inclusive culture
Salary Range
The salary range for this position is $900,000 - $130,000
Final compensation will be determined based on factors such as experience, skills, and qualifications. In line with our commitment to being a great place to work, Lumentum offers competitive total rewards which may include annual bonus, equity, and comprehensive health and welfare benefits.