Modal
Inference Engineering and Product Lead
$300K–$350K
San Francisco · On-site · Full-time · Posted Sep 16, 2026
- Experience
- 10+ years of industry experience, including 3+ years in a leadership role.
About the job
Leads the engineering and product direction of Modal’s LLM inference platform, managing engineers and guiding serving, routing, optimization, and customer-facing product development.
What you'll do
- Recruit, coach, and develop engineers while setting performance expectations and fostering team ownership.
- Drive technical and product decisions and translate frontier-customer needs into platform and product roadmaps.
- Coordinate with compute strategy, go-to-market, and infrastructure teams on accelerator strategy, launches, and roadmaps.
What they ask for
- Track record building high-performance systems at scale.
- Strong background in cloud infrastructure.
- Deep knowledge of low-level OS foundations, such as Linux kernel, file systems, and containers.
Nice to have
- Experience working with LLM inference in production.
- Familiarity with engines, kernels, routing, KV cache management, and speculative decoding.
Pay
$300K – $350K USD base salary
Tools
Linux kernel
AI focus
Leads development of an LLM inference platform, including serving, routing, internal agentic optimization, and user-facing products.
Model-written summary · the original posting is authoritative