SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Preference Model is building automated ML research engineering to advance frontier AI models. The company is addressing a critical bottleneck: existing frontier models are brittle when applied to real-world ML tasks due to lack of high-quality RL training environments. The founding team includes veterans from Anthropic's data team who built infrastructure and datasets behind Claude.
As a Member of Technical Staff in the Capabilities organization, you will design and build reinforcement learning environments that teach frontier models to perform ML engineering and research tasks. This role blends research and engineering, requiring you to stay current with cutting-edge research, develop novel approaches, and implement them in production systems.
Key responsibilities include:
- Designing and implementing RL environments and reward functions that produce clean, learnable signals for frontier models on ML research and engineering tasks
- Building deep expertise across the frontier of ML research, training, and inference infrastructure
- Conducting experiments and evaluations to validate environment designs
- Delivering work into production training runs
- Collaborating with researchers and engineers to brainstorm and create new tools to improve the environment building process
- Taking full ownership and autonomy of the environments you build
Required qualifications:
- 5+ years of experience in machine learning or research, primarily on LLMs and transformer models
- Strong ML fundamentals with broad research interests; ability to read papers deeply and translate them into RLVR problems
- Proficiency in Python and systems programming, plus expertise in PyTorch or JAX
- Problem-solving mindset with end-to-end ownership
- Passion for staying current with ML infrastructure evolution
- Ability to meet throughput expectations and respond quickly to feedback
Desirable qualifications include:
- Expert knowledge in an active deep learning/ML research area with publications or public code
- Research experience (PhD or MS)
- Deep understanding of transformer internals and modern LLM training/inference
- Experience with inference libraries (vLLM, SGLang, etc.)
- Strong kernel development expertise (CUDA, Triton, Pallas)
- Experience building complex interactive RL environments
The company offers competitive compensation (>90th percentile cash and equity), ownership in a fast-moving startup, collaboration with top ML engineers, comprehensive health benefits, 401K match, daily onsite lunch, weekly snacks, and visa sponsorship with relocation support.
