Research Intern, Inference (Winter 2027)
Together AI
This job at a glance
- Who can apply
- New grads and up to 1 year · Bachelor's degree
- Must know
- Data structures & algorithmsContent writingDeep learningPyTorchPython
- Nice to have
- Machine learning
- Work
- On-site in San Francisco · internship
- Pay
- $58–$70 an hour
- Skill demand
- Deep learning10%Data structures & algorithms9%PyTorch7%Content writing2%of 100 similar entry-level jobs posted in the US this week
- Listed
- Nov 1, 2026 · still open
Sign in free to see which of these skills your resume already shows.
About The Role
The Inference Research team is dedicated to building the next generation of efficient, scalable, and reliable serving systems for large foundation models, advancing open and transparent AI. The work intersects cutting-edge model architectures, high-performance systems engineering, and deep hardware optimization, focusing on co-designing software, algorithms, and models to lower the cost and latency of modern AI systems. As a research intern, you will explore distributed inference, compiler-aware optimization, and novel inference-time computation strategies (e.g., speculative decoding, phase-aware execution). Projects involve co-designing and implementing cross-layer optimizations across models, systems, and hardware, with a focus on areas like KV cache design and large-scale serving architectures to unlock performance and scale for foundation models.
Key Responsibilities
- Design and conduct rigorous experiments to validate hypotheses
- Communicate plans, progress, and results to the broader team
- Document findings in scientific publications and blog posts
Requirements & Tech Stack
- Currently pursuing a final year of Bachelor's, Master's, or Ph.D. degree in Computer Science, Electrical Engineering, or a related field
- Strong knowledge of Machine Learning and Deep Learning fundamentals
- Experience with deep learning frameworks (PyTorch, JAX, etc.)
- Strong programming skills in Python
- Familiarity with Transformer architectures and recent developments in foundation models
Preferred Qualifications
- Prior research experience in foundation models, efficient machine learning, or ML systems
- Publications at leading conferences in machine learning or systems (e.g., MLSys, ICLR)
- Experience with CUDA programming (for kernel development)
- Understanding of model optimization techniques and hardware acceleration approaches
- Contributions to open-source machine learning projects
Internship Program Details:
- Duration: 12 to 14 weeks
- Dates: January 4th to April 9th (Winter 2027 cohort)
- Focus: Work alongside industry-leading engineers and researchers.
Compensation:
- Competitive compensation, housing stipends, and other benefits.
- Estimated US hourly rate: $58 to $70.