LLM/ML Engineer (Inference)
San Francisco, CA, US$200k - $300k + equityfull-timePosted 11mo ago
About the role
Designing and implementing scalable inference systems for AI models, optimizing infrastructure, and enabling rapid deployment in a fast-paced, early-stage environment.
Responsibilities
- Architect and implement robust, scalable inference systems for serving state-of-the-art AI models
- Optimize model serving infrastructure for high throughput and low latency at scale
- Develop and integrate advanced inference optimization techniques
- Collaborate closely with research teams to bring new capabilities into production
- Build developer tools and infrastructure for experimentation and deployment
Qualifications
- Deep expertise in Python and PyTorch
- Strong foundation in low-level OS concepts (multi-threading, memory management, networking, storage, performance, scale)
- Experience with modern inference systems like TGI, vLLM, TensorRT-LLM, Optimum
- Ability to create custom tooling for testing and optimization
Skills
Required:PythonPyTorchLow-level OS ConceptsInference Systems
Last updated Mar 18, 2026. Interested? Apply on the company site.
About Reducto
The most accurate API to parse documents
Reducto offers robust and reliable document ingestion for any workflow. Our API allows you to convert complex, unstructured documents into structured outputs that are perfect for RAG, process automation, and more.
documentsartificial-intelligencedata-engineeringenterprise-softwaresearch
More open roles at Reducto
- Founding Data Engineer2w agoSan Francisco, CA · Data/Engineering
- Strategic Projects Lead4w agoHybrid (San Francisco, CA or New York, NY) · GTM / RevOps
- Manager, Sales4w agoSan Francisco, CA · Growth
- Head of Product Engineering1mo agoSan Francisco, CA · Engineering
- Solutions Engineer1mo agoNew York, NY · Solutions