Customer-Facing AI Platform Engineer

Baseten; New York (NY); On-site; USD 200,000 - 400,000; Full time

Benefits offered by this job

Medical, dental & vision for employee+

Flexible PTO including Winter Break

Paid parental leave

Fertility and family-building stipend

401(k) plan

Exposure to ML startups

Job summary

Baseten is seeking Forward Deployed Engineers who will work directly with leading AI customers to own technical outcomes on Baseten. You will manage workloads end-to-end, from problem framing and PoC development to production delivery, tackling complex inference and post-training challenges.

You will design evaluations, respond to incidents, and build automation to accelerate client engagements, while shaping the product roadmap with insights from earned experience across multiple accounts.

Qualifications

• 1-2 years of software engineering experience shipping and maintaining production code.
• Experience debugging complex production issues using logs, metrics, and traces.
• Comfort owning ambiguous technical problems and deciding when to involve others.
• Interest in working directly with customers and influencing the product.
• Clear communication on complex topics with customers or leadership.
• Genuine curiosity about AI inference and training and the infrastructure powering it.
• Willingness to participate in on-call rotations.

Responsibilities

• Act as the account's CTO on Baseten, accountable for workloads' design, run, and scale.
• Translate customer objectives from problem to PoC to production quickly using appropriate tools.
• Design evals and benchmarks to identify quality or performance gaps and close them.
• Respond to mission-critical failures with triage and ownership until fixes ship.
• Build internal tooling and automation for faster engagements and deployable references.
• Shape Baseten's roadmap by channeling customer needs into the product.
• Coordinate across multiple accounts, aligning stakeholders and managing risk.

Skills

Software engineering

Debugging production issues

Customer collaboration

Communication

Ambiguity tolerance

On-call experience

AI infrastructure interest

Education

Bachelor's degree in Computer Science

Tools

Kubernetes

Slurm

Ray

TensorRT

vLLM

PyTorch/JAX

Job description

Baseten is seeking Forward Deployed Engineers who will work directly with leading AI customers to own technical outcomes on Baseten. You will manage workloads end-to-end, from problem framing and PoC development to production delivery, tackling complex inference and post-training challenges.

You will design evaluations, respond to incidents, and build automation to accelerate client engagements, while shaping the product roadmap with insights from earned experience across multiple accounts.