Software Engineer (AI/ML, Infrastructure & Platform)

• We are seeking a Software Engineer, AI/ML (Infrastructure & Platform) to build the foundational systems that power our next generation of AI applications

• This is a systems-focused role. You will design and build the platforms, abstractions, and infrastructure that enable teams to reliably develop, deploy, and scale AI systems — including agentic workflows, retrieval pipelines, and model integrations
• You will operate at the intersection of AI systems and distributed infrastructure, focusing on the “how” behind production AI: how models are orchestrated, how tools/skills are exposed and executed, and how systems are evaluated, monitored, and scaled in real-world environments
• Your work will directly enable product teams to move faster while ensuring our AI systems are reliable, observable, secure, and cost-efficient
• Build core AI infrastructure
• Design and implement platforms for LLM orchestration, tool execution, and agent workflows
• Develop shared services and abstractions used across multiple AI applications
• Build AI capability layers (tools / skills)
• Design and implement tools (“skills”) that agents and applications rely on, including APIs, workflows, and integrations
• Define clear interfaces for capabilities such as data retrieval, calculations, document processing, and external system actions
• Build reusable, composable abstractions that enable safe and scalable tool usage across systems
• Ensure tools are reliable, observable, and secure, especially when interacting with sensitive data
• Enable agentic systems at scale
• Build infrastructure to support multi-step agents (state management, tool routing, retries, failure handling)
• Design systems where agents reason over and invoke tools/skills reliably
• Create reusable orchestration patterns between models and capabilities
• Develop evaluation and observability systems
• Build frameworks for offline and online evaluation of AI systems
• Implement logging, tracing, and monitoring for model behavior and system performance
• Own reliability and performance
• Design systems for high availability, fault tolerance, and graceful degradation
• Optimize for latency, throughput, and cost across AI workloads
• Build data and retrieval infrastructure
• Develop scalable RAG pipelines, indexing systems, and data processing workflows
• Own infrastructure for handling large-scale structured and unstructured data
• Create internal platforms and developer tooling
• Build tools, SDKs, and internal platforms that enable engineers to integrate AI capabilities quickly and safely
• Standardize best practices across teams (prompting, evaluation, deployment)
• Work closely with product and AI teams
• Partner with AI Applications engineers to support production use cases
• Translate product needs into scalable infrastructure solutions

Benefits

• Company equity managed through Carta
• Unlimited PTO in an environment where taking time off to relax or recharge is supported and encouraged
• Full medical and dental benefits
• 401k with Match and 100% vesting upon hire
• Fully remote, flexible work environment (we do however meet together in person several times a year)
• Paid parental leave

Apply tot his job Apply To this Job