Sr. Staff Software Engineer, Cribl AI

Why You'll Love This Role

Join Cribl's AI Systems team and help build the foundational infrastructure powering Generative and Agentic AI capabilities across Cribl's product suite.

You'll work at the intersection of distributed systems, AI inference infrastructure, model routing, and agentic technologies, building scalable platforms that enable our Product and Research teams to develop, evaluate, and bring cutting edge AI capabilities into production.

Our team is responsible for building and operating critical AI infrastructure, including multi provider model routing, inference services, Model Context Protocol (MCP) integrations, AI observability, and SecIT benchmarking and evaluation systems for IT and security workflows.

You'll have the opportunity to solve challenging engineering problems spanning performance, scalability, reliability, and cost efficiency while shaping the architecture of AI systems used across Cribl's products.

You'll collaborate closely with research, and product teams to turn emerging AI capabilities into production ready systems that deliver real customer value.

On top of it all, you'll have fun. Cribl strives to be a great place to work for everyone.

As An Active Member Of Our Team, You Will...

• Work closely with Product and Research engineering teams to prototype, experiment with, evaluate, and productionize new AI capabilities.

• Design, build, and operate scalable, highly available backend services and distributed systems supporting AI/ML workloads.

• Develop and optimize model routing and inference infrastructure across multiple LLM and model providers, balancing latency, throughput, reliability, and cost.

• Build infrastructure supporting agentic AI applications, including MCP integrations, tool connectivity, and secure interactions with enterprise systems.

• Develop and maintain AI observability, evaluation, and benchmarking systems to measure model quality, inference performance, and production reliability.

• Bridge research and production by building scalable AI/ML infrastructure, evaluation frameworks, and data pipelines.

• Productionize, launch, and operate AI-based technologies integrated into Cribl's core products, solving real world customer problems.

• Drive technical architecture and design decisions, identifying tradeoffs across scalability, performance, operational complexity, and maintainability.

• Evaluate emerging AI models, inference technologies, and frameworks for production readiness and adoption.

• Collaborate across engineering teams, contribute to technical design reviews, and help establish best practices for building reliable AI powered systems.

• Mentor and coach junior engineers, providing technical guidance and support through design reviews, code reviews, and hands-on collaboration to help them grow their technical skills and engineering judgment.

• Participate in oncall rotations and support the operational reliability of production AI services.

If You've Got It – We Want It

• Bachelor's degree in Computer Science, Engineering, or equivalent practical experience, with 7+ years of software engineering experience.

• Strong experience designing, building, and operating distributed systems, scalable backend services, or cloud-native infrastructure.

• Proficiency in one or more programming languages, such as Go, Python, or TypeScript.

• Experience building, integrating, or operating production AI/ML systems, including NLP, speech/voice or MLOps based platforms.

• Experience with AI/ML infrastructure or LLM application architectures, such as model routing, inference platforms, MCP, RAG, or evaluation frameworks.

• Experience with cloud infrastructure, API design and production observability.

• Understanding of performance optimization, scalability, reliability, and operational troubleshooting in production environments.

• Ability to independently drive technical initiatives, make architectural tradeoffs, and collaborate with Product, Research, and Engineering leadership.

• Strong problem solving skills and the ability to navigate ambiguity while maintaining focus on customer and business outcomes.

Nice to Have

• Hands on experience with model inference runtimes such as ONNX, NVIDIA Triton, vLLM, or TensorRT-LLM.

• Experience deploying and optimizing ML models across cloud infrastructure, GPUs, or resource constrained edge devices.

• Familiarity with inference optimization techniques, including quantization, dynamic batching, KV cache and hardware aware scheduling to improve latency, throughput, and cost efficiency.

• Experience with model serving, inference benchmarking, performance profiling, and detecting model quality or performance regressions.

• Experience building or operating high throughput, low latency inference systems at scale.

• Familiarity with fine tuning, model optimization, or deploying custom NLP, speech, or other ML models.

• Experience with distributed tracing, AI observability and inference optimizations.

• Experience designing secure, multi tenant platforms, workload isolation, and resource management.

• Contributions to open source AI infrastructure, inference frameworks, or developer tooling.