Client-Facing ML Systems Engineer – Production & Performance

Wafer; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Medical insurance

Dental and vision

Unlimited PTO

Parental leave

Housing stipend

Relocation assistance

Uber/Waymo transportation

Visa sponsorship

Job summary

Wafer in San Francisco seeks a Member of Technical Staff, Forward Deployed to drive production deployment of AI workloads and collaborate with customers from benchmark to production. You will work with performance engineers to ensure fast, healthy workloads and address production challenges with pragmatic, scoped solutions.

The role emphasizes hands-on engineering, customer interaction and rapid iteration, with on-site work five days a week in San Francisco.

Qualifications

• Experience shipping and operating production systems.
• Ability to read a trace, open a profiler and find the problem.
• Own a technical customer relationship and explain results to a skeptical engineering team.
• Able to defend a benchmark methodology and adapt approaches without a full spec.

Responsibilities

• Run the technical evaluation on the customer's workload, understand traffic and latency targets, and explain results.
• Get each customer into production on Wafer, collaborating with engineers to meet targets.
• Own the health of accounts: monitor latency, errors and usage, and engage proactively.
• Scope fixes across engine, kernels or agents and provide the right data for engineering.
• Build tools, integrations and runbooks to accelerate deployments with each release.
• Communicate customer needs to engineering and sales based on production observations.

Skills

Production systems

Customer relations

Benchmarking

LLM inference

Job description

Wafer in San Francisco seeks a Member of Technical Staff, Forward Deployed to drive production deployment of AI workloads and collaborate with customers from benchmark to production. You will work with performance engineers to ensure fast, healthy workloads and address production challenges with pragmatic, scoped solutions.

The role emphasizes hands-on engineering, customer interaction and rapid iteration, with on-site work five days a week in San Francisco.