Sr. Staff Software Engineer, Cribl AI

Role overview Build foundational AI infrastructure that helps product and research teams move new generative and agentic AI capabilities into production. The work spans distributed systems, model routing and inference, integrations for AI agents, and the monitoring and evaluation needed to operate these systems reliably at scale. The role includes technical architecture, mentoring, and participation in on-call support.

Responsibilities - Design, build, and operate scalable backend services and distributed systems for AI and machine learning workloads. - Develop model routing and inference services across providers, balancing latency, throughput, reliability, and cost. - Create infrastructure for agentic applications, including Model Context Protocol integrations, tool connections, and secure access to enterprise systems. - Build observability, evaluation, benchmarking, and data pipeline capabilities to measure model quality and production performance. - Work with product, research, and engineering teams to prototype, assess, and productionize AI capabilities for customer use. - Guide architecture and design decisions, mentor engineers, review technical work, and help maintain production reliability through on-call rotations.

Requirements - Bachelor’s degree in computer science or engineering, or equivalent practical experience, and at least seven years in software engineering. - Strong background designing and operating distributed systems, scalable backend services, or cloud-native infrastructure. - Proficiency in one or more of Go, Python, or TypeScript. - Experience building, integrating, or operating production AI or machine learning systems. - Ability to make sound technical trade-offs involving scalability, performance, reliability, operational complexity, and maintainability. - Strong collaboration and problem-solving skills, including the ability to work through ambiguity and communicate with product, research, and engineering partners.

Nice to have - Experience with inference runtimes such as ONNX, NVIDIA Triton, vLLM, or TensorRT-LLM; GPU deployments; or inference optimization techniques such as quantization and dynamic batching. - Background in model serving, benchmarking, performance profiling, AI observability, distributed tracing, or detecting model regressions. - Experience with secure multi-tenant systems, workload isolation, resource management, or open-source AI infrastructure.

Benefits and work setup The role is described as remote-first. The listed base salary range is $250,000–$300,000 USD, with eligibility for a corporate bonus program, equity, health, dental and vision coverage, disability and life insurance, paid holidays, paid time off, a 401(k), and a fertility treatment benefit.