About the role
Member of Technical Staff
Inference performance depends on how efficiently models use the underlying hardware. Techniques across kernels, compilers, runtimes, and serving systems can dramatically improve latency and throughput, but these optimizations are difficult, hardware-specific, and slow to reproduce across new accelerators. And none of it counts until it is running in a customer's production traffic.
At Wafer, we are building AI systems that automatically optimize inference workloads across silicon. The goal is fungible token capacity. Any accelerator optimized toward serving inference most efficiently.
Wafer is well funded and serves trillions of tokens a month for mission critical workloads. We serve the highest performance inference to fast-growing AI startups.
Members of Technical Staff build the systems that make that possible: the kernels, runtimes, agents and infrastructure behind every workload we serve. Our forward deployed engineers run customer deployments day to day and bring you in on the hardest problems.
What you'll do
- Develop and optimize high-performance computing kernels, and work across inference engine internals and serving infrastructure
- Develop AI agents to do autonomous inference engineering
- Design, deploy, and operate heterogeneous clusters across vendors
- Take on the hardest customer problems. When a workload needs a fix in the engine, the kernels or the agents, our forward deployed engineers bring it to you and you solve it
- Inform product roadmap. You sit closer than anyone to how Wafer behaves under real load, and the engineering team builds against what you report
What we look for
- You are an exceptional engineer. You have shipped and operated production systems, and you can still open a profiler, read a trace, and find the problem yourself. Inference experience helps, but it matters more that you can be handed an unfamiliar system and own it inside a week.
- You are credible in a room full of engineers. You can take a skeptical ML team through a benchmark, defend the methodology, and concede the point when they are right.
- You work without a spec. The problem arrives half-defined from a customer who does not yet know what they need, and you come back with a scoped answer rather than a list of questions.
How we evaluate
We score every candidate on seven values:
- Infinitely Resourceful
- Exceptionalism
- Unreasonable Standards
- Company Over Self
- High EQ
- Learns Quickly
- First Principles Thinker
Compensation and benefits
- $250K + generous equity.
- Fully covered medical, dental, and vision insurance.
- Daily lunch and dinner, unlimited PTO, and parental leave.
- $1K/month housing stipend (post-tax) if you live within walking distance (0.5 miles) from the office.
- Covered Uber/Waymo from/to office.
- Relocation allowance and benefits.
- Visa sponsorship available.
How we work
On-site in San Francisco, five days a week. Small team with massive surface area and ownership. You operate with complete autonomy of how to solve problems. We don't see engineers as code writers, but as problem solvers. You will work across the stack to build a company scaling extremely quickly.
This is not a role that lives in meetings. Nearly all of your time is engineering. What makes it different is who that engineering is for: you are responsible for a named set of customers, their workloads run on what you build, and you are the person they hear from when it matters.