Search
Go
Software Engineer, Inference
Summary by AIEngineer.careers
Software Engineer, Inference is a AI Infrastructure Engineer role (full-time). with Thinking Machines Lab (Andreessen Horowitz). in SAN FRANCISCO, US. Compensation shown: $300K–$400K. Imported listing (source: jobs.a16z.com). Apply on the employer's site (jobs.a16z.com).
Imported listing (source: jobs.a16z.com) · Apply on jobs.a16z.com
SAN FRANCISCO · US
$300K–$400K
Full-time
MID
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from jobs.a16z.com
Join Thinking Machines Lab to own the reliability, scale, and efficiency of systems serving AI models to users. This role ensures that research breakthroughs are safely deployed into production environments with high performance. You will focus on optimizing inference pipelines and maintaining robust infrastructure.
Responsibilities
- Own reliability, scale, and efficiency of model serving systems
- Ensure research gains reach production safely
- Optimize inference performance for user-facing applications
Requirements
- Experience in building scalable software systems
- Strong understanding of model serving and inference architectures
- Ability to bridge research innovations with production engineering
Nice to Have
- Background in AI/ML infrastructure
- Experience with large-scale distributed systems
Tech Stack
Inference OptimizationModel ServingScale
TM
Thinking Machines Lab (Andreessen Horowitz)
San Francisco · US · 240+ employees
Thinking Machines Lab is a San Francisco-based artificial-intelligence research and product company founded in 2025. It aims to make AI knowledge and tools broadly useful and develops AI systems and platforms, including the Inkling open-weights model and Tinker fine-tuning API.
