Customer‑Facing AI Systems Engineer – Scale & Deploy

AI Chopping Block; San Francisco, Northern (CA, KY); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Competitive comp

Equity

Full benefits

Flexible PTO

Winter break

Parental leave

Fertility stipend

401(k) plan

ML startup exposure

Job summary

Baseten is seeking a Forward Deployed Engineer to work with leading AI companies, owning outcomes on Baseten across the model lifecycle. You will frame customer problems, define success criteria, build PoCs, and drive production deployments with focus on reliability and scalability.

You will collaborate with customers and internal teams, communicate clearly across engineers and leadership, and expand Baseten's infrastructure to support fast, repeatable deployments at scale.

Qualifications

• Minimum 1-2 years of software engineering experience, shipping and maintaining code in large production systems.
• Experience debugging complex production issues - logs, metrics, and traces to root-cause problems in unfamiliar systems.
• Confidence owning ambiguous technical problems and making decisions under uncertainty, knowing when to pull in others.
• Motivation beyond pure engineering: interest in working directly with customers and influencing the product.
• Clear communication on complex technical topics with customers' engineers or leadership.
• Genuine curiosity about AI inference and training and desire to become an infrastructure expert.
• Willingness to respond to customers outside regular hours and participate in an on-call rotation.
• Excitement about solving problems for large, fast-growing AI workloads.

Responsibilities

• Act as each account's de facto CTO on Baseten, accountable for workload design, execution, and scalability.
• Take customer objectives from vague to shipped: frame the problem, define the spec, build the PoC, and productionize quickly.
• Design evals and benchmarks to isolate quality or performance gaps and close them via inference optimization or post-training improvements.
• Be the first responder to mission-critical failures, triaging and owning fixes or routing to the owning team until it ships.
• Build internal systems to make each engagement faster, including tooling for eval and deployment infra and reference implementations.
• Shape the product by channeling account needs into the roadmap and shipping fixes/features into Baseten's codebase.
• Handle multiple accounts simultaneously, sequencing work and keeping customers and stakeholders aligned on status and risk.

Skills

Software engineering

Production debugging

Ownership under uncertainty

Customer-facing

Communication

AI inference curiosity

On-call readiness

Problem solving at scale

Tools

Kubernetes

Slurm

Ray

GPUs

PyTorch / JAX

vLLM / TensorRT-LLM

Job description

Baseten is seeking a Forward Deployed Engineer to work with leading AI companies, owning outcomes on Baseten across the model lifecycle. You will frame customer problems, define success criteria, build PoCs, and drive production deployments with focus on reliability and scalability.

You will collaborate with customers and internal teams, communicate clearly across engineers and leadership, and expand Baseten's infrastructure to support fast, repeatable deployments at scale.