As a Software Engineer on the AI Infrastructure & Developer Experience team at Lyft, you will design and build the foundational infrastructure that enables AI development at scale. You'll create frameworks for LLM integration, build intelligent agents for developer workflows, and establish best practices for AI safety, observability, and cost management. You'll collaborate across teams to democratize AI capabilities while ensuring reliability, security, and responsible AI usage. Your work will directly impact how every engineer at Lyft leverages AI from AI-assisted coding to automated upgrades to data analysis.
Responsibilities:
- Design, build, and maintain AI infrastructure platforms including LLM gateways, prompt management systems, vector databases, and agent orchestration frameworks.
- Build intelligent agents and AI-powered automation to enhance developer workflows across the software development lifecycle (code generation, testing, review, documentation, incident response).
- Develop centralized automation workflow services and tools focused on an easy to use, streamlined, and user friendly UI experience.
- Implement observability, monitoring, and cost management systems for AI infrastructure and LLM usage across the organization.
- Plan and execute high-level cross-team AI infrastructure projects from inception to delivery, including model evaluation pipelines and AI safety guardrails.
- Partner with ML Platform, Infrastructure, and product engineering teams to understand AI use cases, debug integration issues, and design scalable AI solutions.
- Establish best practices and golden paths for LLM integration, prompt engineering, RAG implementations, and agent development.
- Write well-crafted, well-tested, readable, and maintainable code for AI infrastructure components.
- Lead incident responses for AI infrastructure issues, mentor the team on operational best practices, and implement long-term systemic fixes.
- Build internal tooling for prompt testing, model comparison, AI performance benchmarking, and cost optimization.
- Participate in the team's on-call rotations for AI infrastructure systems.
- Mentor engineers across the organization on AI infrastructure best practices and responsible AI development.
Experience:
- Bachelor's degree in Computer Science or a related field, or equivalent experience.
- 3+ years of experience in software development, distributed systems, and infrastructure engineering.
- Experience building or integrating with AI/ML systems, LLM APIs (OpenAI, Anthropic, etc.), or AI infrastructure platforms.
- Strong understanding of LLM capabilities, limitations, prompt engineering, and AI safety considerations.
- Experience with API design, SDK development, and building developer-facing platforms or frameworks.
- Proficiency in Python and/or Go for building scalable AI infrastructure and tooling.
- Experience with Kubernetes, containerization, and cloud infrastructure at scale.
- Familiarity with vector databases, using embedding models, and RAG architectures.
- Proven ability to design and build robust, scalable infrastructure components.
- Experience with observability tools, distributed tracing, and monitoring systems.
- Ability to write clear technical documentation and design specifications for AI systems.
- Bonus:
- Experience building AI agents, multi-agent systems, or agentic workflows.
- Hands-on experience with agent frameworks (LangChain, LangGraph, ReAct, etc.) or building custom orchestration systems.
- Experience with fine-tuning, model evaluation, or AI practices.
- Familiar with front-end frameworks and UI design.
- Background in developer experience, developer tools, or platform engineering.
- Experience implementing AI safety measures, content filtering, or guardrails.
- Contributions to open-source AI infrastructure projects.
- Experience with cost optimization strategies for LLM usage at scale.
- Knowledge of responsible AI practices, bias mitigation, and AI governance.
