Software Engineer, Production Inference (Distributed Inference)
Thinking Machines Lab · San Francisco
CHECKED 13H AGO
Frontier labonsite$350k–$500k
At a glance
Highlights
- Build and scale distributed inference serving Inkling and Tinker in production.
- Own fast, reliable, cost-efficient serving from training to production.
- Partner with research to bring new model architectures to production.
What they offer
- Generous health, dental, and vision benefits
- Unlimited PTO
- Paid parental leave
- Relocation support as needed
Ideal candidate
Systems-oriented engineer who thrives operating large-scale production services and cares about latency, reliability, and efficiency. You enjoy partnering with research to bring evolving models into robust real-world serving.
Requirements
- 3+ years of experience building and operating distributed systems in production
- Strong systems programming skills in Python, C++, Rust, or similar languages
- Experience with production infrastructure at scale, including reliability, observability and performance
- Solid understanding of networking, concurrency, and distributed systems fundamentals
- visa sponsorship
- We sponsor visas
Lab profile
About Thinking Machines Lab
Builds frontier AI that extends human will and judgment through customizable models and interfaces.
What they build
- Inkling frontier models
- Tinker model customization
- Human-AI communication interfaces
Known for
- Frontier model training
- Post-training and reinforcement learning
- Evaluation infrastructure
- GPU supercomputing and reliability