Baseten
Forward Deployed Engineer (Training)
About this role
Baseten seeks a Forward Deployed Engineer to serve as technical leader for major AI companies, owning their inference and model serving outcomes on the platform. You'll span the full model lifecycle—from optimization and post-training to production scaling—while building internal systems and shaping product roadmap based on customer needs.
What you'll do
- Act as de facto CTO for customer accounts, owning workload design, deployment, and scaling on Baseten
- Transform vague customer objectives into shipped solutions by framing problems, defining specs, building POCs, and deploying to production
- Design and execute evals and benchmarks to identify performance gaps, then optimize inference, improve models through post-training, or refine evals
- Triage and own mission-critical production failures, routing to appropriate teams while maintaining accountability
- Build internal tooling and automation for eval and deployment infrastructure to accelerate future engagements
- Influence product roadmap by channeling customer needs and contributing code fixes and features directly to Baseten's codebase
What they're looking for
- Production software engineering and full-stack debugging across large systems
- Complex production issue triage using logs, metrics, and traces
- AI inference engines (vLLM, TensorRT-LLM, SGLang) and LLM architecture knowledge
- GPU workload profiling and optimization for training or serving
- Distributed compute platforms (Kubernetes, Slurm, Ray) and infrastructure domains (storage, networking)
- Deep learning frameworks (PyTorch, JAX) and post-training techniques (SFT, RL)
- Clear technical communication with engineers and leadership
- On-call operations and incident response leadership
Benefits
- Competitive compensation with meaningful equity
- 100% medical, dental, and vision insurance coverage for employee and dependents
- Flexible PTO policy
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Baseten
Baseten builds an AI inference platform that enables companies to deploy and manage machine learning models in production at scale. The company is hiring software engineers, infrastructure specialists, and product engineers to develop observability systems, frontend experiences, reliability infrastructure, developer tools, and enterprise deployment solutions.
- Website
- baseten.com
Likely interview questions
- Tell us about a complex production issue you debugged—walk us through your triage process and how you identified the root cause.
- Describe a time you owned an ambiguous technical problem with incomplete information. How did you approach it and when did you involve other specialists?