Baseten
Forward Deployed Engineer (Training)
$200K–$400K
San Francisco +1 · Hybrid · Full-time · Posted Aug 19, 2026
- Location
- San Francisco
New York - Experience
- Minimum 1–2 years of software engineering experience.
About the job
Own customer technical outcomes on Baseten by deploying, optimizing, and improving AI models and their infrastructure from proof of concept through production.
What you'll do
- Design and ship customer solutions, including proofs of concept, production deployments, evaluations, and model or inference improvements.
- Respond to production incidents and remain accountable for fixes; build tools and automation to make future engagements faster.
- Influence Baseten’s product roadmap and codebase while coordinating work across customer accounts and internal teams.
What they ask for
- At least 1–2 years of software engineering experience shipping and maintaining code in large production systems.
- Experience debugging complex production issues using logs, metrics, and traces.
- Ability to own ambiguous technical problems and communicate complex topics clearly.
- Willingness to support customers outside regular working hours and participate in an on-call rotation.
Nice to have
- Experience with distributed compute platforms, LLM architectures and inference engines, GPU optimization, or post-training techniques.
- Infrastructure or operational depth, such as storage, networking, incident response, or distributed systems.
Pay
$200K – $400K (base salary)
Tools
Kubernetes, Slurm, Ray, InfiniBand, RoCE, vLLM, TensorRT-LLM, SGLang
AI focus
Work on AI inference and training, including model evaluation, inference optimization, and post-training.
Model-written summary · the original posting is authoritative