Software Engineer II

The Safety Engineering - Triage & Insights Team owns and builds systems and customer-facing products across web, mobile, and API surfaces that help fleets identify unsafe driving behaviors and recognize positive driving habits. The team is building AI-native safety products, including LLM-powered workflows, agentic systems, and conversational experiences.

• Own customer-facing features and platform capabilities end to end, from design and implementation through rollout and follow-through in production, including taking AI prototypes to production at scale.
• Architect, build, test, and deliver full-stack products across reliable services, APIs, and web and mobile experiences, using technologies such as Golang, GraphQL, TypeScript, React, React Native, and MySQL.
• Build AI-native product experiences: integrate LLMs into safety workflows, develop agent tooling and retrieval-augmented generation (RAG), and design the interactions between AI agents and the product UI.
• Design and run evaluations and build human-in-the-loop feedback loops that continuously improve the accuracy, precision, and reliability of the insights we deliver.
• Use AI coding tools and agents in your own workflow to plan, build, and ship faster.
• Make thoughtful technical tradeoffs across speed, maintainability, scalability, cost, and customer impact.
• Own the operational health of the production systems you build, improving reliability and scalability as our customer base grows.
• Collaborate across Engineering, Product, Design, ML, and platform teams to deliver cohesive customer experiences.

• 3+ years of professional software engineering experience building, shipping, and operating reliable customer-facing production systems.
• Strong programming fundamentals in a language such as Golang, Java, or Python, with experience writing clean, maintainable code and reviewing peers' code for correctness and clarity.
• Experience developing features or end-to-end solutions across backend services, APIs, and modern web applications.
• Experience or demonstrated interest in AI-native development, including integrating LLMs into products, building agentic workflows, or running evaluations to improve the quality of AI-generated output.
• Experience using data, metrics, logs, tests, or tracing to investigate issues, validate releases, and improve reliability.
• Ability to independently own moderately complex projects, with the ability to estimate, communicate, and deliver on milestones.
• Strong communication and collaboration skills across engineering and cross-functional partners.

• Experience building and scaling customer-facing AI or LLM-powered products in production, including agent tooling, RAG, prompt engineering, or conversational and voice experiences.
• Experience with LLM evaluation and observability tools such as Langfuse or Eino, and optimizing LLM-powered systems for cost and token efficiency.
• Experience working across the stack with modern technologies such as Go, GraphQL, TypeScript, React, React Native, and AWS (or Azure or Google Cloud).
• Familiarity with observability, rollout practices, and monitoring approaches that improve product reliability and operational excellence.

Annual base salary range: $113,645—$191,000 USD. Eligible for an initial RSU grant with no vesting cliff, and ongoing refresh opportunities tied to performance. Total rewards include performance-based bonus/variable pay, equity, flexible remote model, professional development stipend, comprehensive health and parental leave plans.

Apply through the Samsara careers page. For accommodations, email accessibleinterviewing@samsara.com.