AI Inference Tools Engineer — Build Developer Tools

Modular; United States; Hybrid; USD 167,000 - 242,000; Full time

Benefits offered by this job

Stock options

401k matching (up to 5%)

Flexible PTO

Team onsite events

Job summary

Modular is building a next‑gen AI platform and aims to empower developers with powerful tooling for the MAX framework. As part of the MAX Tools team, you will create and maintain dev tools to debug, profile, and optimize AI models and kernels.

You will work on profiling, tracing, and observability tooling across the stack, with flexible in-office/remote options for experienced candidates. Hybrid work across multiple locations is possible.

Qualifications

• Experience designing, building, and shipping developer tools or observability systems.
• Fluency in systems languages (C++, Rust, Go) and user-facing language (Python).
• Experience profiling, tracing, benchmarking to improve performance.
• Strong written communication and ability to work independently in a distributed team.

Responsibilities

• Enhance the MAX developer experience by adding tools across the AI stack and hardware platforms.
• Design, build, and maintain profiling, tracing, debuggers, and dashboards for MAX deployments.
• Create agent-native tooling to support human and agent workflows.
• Connect MAX tools across the stack and with orchestration layers above.
• Participate in design discussions and code reviews to uphold high standards.
• Collaborate with kernel, model, and serving engineers to convert pain points into better tools.

Skills

C++

Rust

Go

Python

Profiling

Tracing

Benchmarking

Distributed work

User-facing tools

Tools

Nsight Systems

Nsight Compute

rocprof

Perfetto

Job description

Modular is building a next‑gen AI platform and aims to empower developers with powerful tooling for the MAX framework. As part of the MAX Tools team, you will create and maintain dev tools to debug, profile, and optimize AI models and kernels.

You will work on profiling, tracing, and observability tooling across the stack, with flexible in-office/remote options for experienced candidates. Hybrid work across multiple locations is possible.