Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Target Resume Now
About the Role
We build the fastest GPU compiler in the world, enabling customers to turn their dataset into a specialist model in days. This role involves owning the end-to-end modeling process, including SFT, RL, DPO, designing evaluations, and distillation.
Responsibilities
- Own the post-training pipeline end-to-end: data curation, SFT, preference optimization, RL, evals, distillation and finally deployment
- Design reward functions and RL looks along customer domain experts
- Build an eval harness trustworthy enough to make a ship/no-ship call within a short window
- Structure and generate datasets, including synthetic data pipelines
- Distill specialist models down into smaller models
- Drive the time-to-model by identifying and removing critical path bottlenecks
- Embed with customers as a forward-deployed researcher and hand over pipelines cleanly
Requirements
- Shipped post-trained models into production and can discuss tradeoffs
- Hands-on depth across SFT and RL (DPO, GRPO, PPO or similar)
- Ability to judge evaluation honestly: what to measure, what a result means, and when a number is misleading
- Comfortable owning data: curation, filtering, labeling workflows and synthetic generation
- Proficient in PyTorch or JAX
- Willing to collaborate with customers' domain experts to translate intuition into reward functions
Skills
- SFT
- RL
- DPO
- GRPO
- PPO
- PyTorch
- JAX
- Data Curation
- Synthetic Data Generation
- Model Distillation
- Evaluation Design
- Reward Function Design
Location
- San Francisco
Work Type
- Full-time
- Onsite
Experience Level
- Member of Technical Staff
Salary/Compensations
- $275,000-$315,000
Benefits
- Meaningful equity
- Relocation assistance
About the Company
- SF Tensor is building the future of high-performance compute for AI by rethinking and rebuilding the stack from hardware to cloud.
- We are developing a Kernel Optimizer and a Model Foundry to make compute faster, cheaper, and more available.
- Backed by Susa Ventures, Y Combinator, and other notable investors and industry leaders.
- We believe that advancements in AI require corresponding leaps in compute power.