Software Engineer, Inference

Thinking Machines Lab•San Francisco, CA

16h•$300,000 - $350,000•Onsite

About The Position

We're hiring a Software Engineer, Inference to own the reliability, scale, and efficiency of the systems that serve our models to real users. Our research and inference teams push the limits of model performance and serving efficiency; this role makes sure those gains reach production safely and stay up — powering Tinker's live, multi-tenant serving and the products built on top of our models. This is a production-facing systems role at the center of the company. You'll be the bridge between cutting-edge inference techniques and the day-to-day reality of serving real traffic: rollouts, capacity, incidents, and everything that keeps a fast-growing platform online.

Requirements

Experience operating large-scale, latency-sensitive production systems
Proficiency in Python and Go or another systems language
Experience with observability, monitoring, and incident response for production services
Strong understanding of distributed systems and how they fail at scale

Nice To Haves

Experience running production inference for large language models or other large-scale ML systems
Experience with deployment and rollout systems, such as canarying, blue/green deploys, or feature flags
Experience with capacity planning and cost optimization for GPU or TPU infrastructure
Familiarity with inference-specific techniques, such as batching, caching, or quantization, and their operational implications
Comfortable being on-call and leading incident response for critical production systems
Comfortable working with high autonomy in a fast-changing, early-stage environment

Responsibilities

Operate and scale the production inference systems that serve live traffic, including Tinker's multi-tenant serving platform
Own the rollout process for new models, model versions, and inference optimizations, ensuring safe, incremental deployment to production
Build and improve observability, alerting, and capacity planning so the team can detect, diagnose, and resolve production issues quickly
Partner with inference and research teams to productionize new serving techniques without compromising reliability
Lead incident response for production inference issues, driving root cause analysis and durable fixes
Design for graceful degradation, failover, and redundancy so that serving stays resilient as usage grows
Manage capacity and cost tradeoffs for serving infrastructure as traffic and model sizes scale