Customer-Facing AI Infrastructure Engineer

FDE Times; San Francisco (CA); On-site; USD 140,000 - 230,000; Full time

Benefits offered by this job

Competitive comp & equity

Medical, dental, vision (US)

Flexible PTO

Parental leave

Fertility stipend

401(k)

Learning opportunities

Job summary

Baseten is seeking Forward Deployed Engineers who work directly with the world's largest AI customers, owning their technical outcomes on Baseten and tackling the hardest problems in model serving at scale. You’ll oversee the full lifecycle from inference to post-training, ensuring workloads are designed, run, and scaled efficiently.

Effective communication with customers and leadership, deep curiosity in AI inference and training, and the ability to operate under on-call conditions are

Qualifications

• Minimum 1–2 years of software engineering experience shipping and maintaining code in large production systems.
• Experience debugging production issues using logs, metrics, and traces to root-cause problems.
• Comfort owning ambiguous technical problems and deciding when to pull in others.
• Motivation to work directly with customers and influence the product.
• Clear communication on complex topics to customers and leadership.
• Genuine curiosity about AI inference and training and infrastructure.
• Willingness to respond to customers outside normal hours and participate in on-call rotations.

Responsibilities

• Act as account CTO on Baseten, accountable for workloads designed, run, and scaled.
• Translate customer objectives into shipped solutions from PoC to production quickly.
• Design evals and benchmarks to identify quality or performance gaps and close them.
• Be first responder for mission-critical failures and triage or route to owning team.
• Build internal systems to speed engagement, including tooling and automation for eval and deployment infrastructure, plus reference implementations.
• Shape the product by feeding account needs into the roadmap and shipping fixes/features to Baseten's codebase.
• Coordinate across multiple accounts, align stakeholders on status and risk.

Skills

Software engineering

Debugging complex prod issues

Customer-facing involvement

Ambiguity ownership

Effective communication

On-call readiness

Account cross-sharing

Tools

Kubernetes

Slurm

Ray

vLLM

TensorRT-LLM

SGLang

PyTorch

JAX

Job description

Baseten is seeking Forward Deployed Engineers who work directly with the world's largest AI customers, owning their technical outcomes on Baseten and tackling the hardest problems in model serving at scale. You’ll oversee the full lifecycle from inference to post-training, ensuring workloads are designed, run, and scaled efficiently.

Effective communication with customers and leadership, deep curiosity in AI inference and training, and the ability to operate under on-call conditions are