Staff AI Platform Engineer
New
L
Life360AI infrastructure
Location: Remote, USA; remote work environment ... can be performed remotely (within the US)Full-TimeStaff
SalaryThe US-based salary range for this position is $149,000 to $271,500 USD.
Apply NowOpens the employer's application page
Job Details
- Experience
- 8+ years of engineering experience, including 3+ years building platforms or infrastructure used by other engineers
- Required Skills
- RESTful APIsDistributed Systems
Requirements
- Have 8+ years of engineering experience.
- Have 3+ years building platforms or infrastructure used by other engineers.
- Have experience building and operating production AI systems, such as agentic workflows, LLM integrations, retrieval, and evaluation.
- Have working knowledge of MCP and agent orchestration, including controlled connections between agents and internal systems.
- Bring strong backend and cloud fundamentals, including distributed systems, APIs, and infrastructure as code.
- Apply reliability and observability practices.
- Have experience running AI inference in production, including latency, reliability, provider management, and cost tradeoffs.
- Use sound judgment in deciding when to invest in shared platforms.
- Write clear design documents and standards that other engineers can build against.
- Use AI coding assistants for substantive work and review AI-generated code with ownership and accountability.
Responsibilities
- Establish the vision and paved paths for AI-native engineering practices across Life360.
- Build the agent runtime and orchestration platform, including identity, authorization, and audit for scheduled and unattended agents.
- Operate MCP gateway and connector infrastructure for managed, auditable access to internal data, APIs, repositories, and SaaS tools.
- Support the LLM gateway, including model access and routing, authentication, rate limits, token budgets, and cost attribution.
- Build evaluation and regression infrastructure, including datasets, offline evaluations, CI hooks, and result storage.
- Set up observability for prompts and responses, request costs, quality signals, and drift.
- Work with Security, Privacy, and Legal on data handling, tenant isolation, and auditability.
- Define how product teams access, run, and monitor production AI inference, including serving, latency, reliability, and provider management.
- Own production components, including SLOs, dashboards, deployment pipelines, and incident response.
- Develop shared memory, retrieval, and knowledge capabilities, and partner with AI DevX and Agentic PDLC on reusable platform primitives.
View Full Description & ApplyYou'll be redirected to the employer's site
