LLM Inference Frameworks and Optimization Engineer
Together AI · San Francisco, Singapore · Research
About this role
Together AI is hiring a mid-level AI Engineer in the machine learning function based in San Francisco, Singapore. The posting calls out experience with Python, CUDA, Kubernetes, PyTorch and roughly 3+ years of relevant work. Compensation is listed at $160,000–$230,000 per year.
- Role
- AI Engineer
- Function
- machine learning
- Level
- mid
- Track
- Individual contributor
- Employment
- Full-time
- Location
- San Francisco, Singapore
- Experience
- 3+ years
- Department
- Research
More roles at Together AI
Job description
from Together AI careersAbout the Role
At Together.ai, we are building state-of-the-art infrastructure to enable efficient and scalable inference for large language models (LLMs). Our mission is to optimize inference frameworks, algorithms, and infrastructure, pushing the boundaries of performance, scalability, and cost-efficiency.
We are seeking an Inference Frameworks and Optimization Engineer to design, develop, and optimize distributed inference engines that support multimodal and language models at scale. This role will focus on low-latency, high-throughput inference, GPU/accelerator optimizations, and software-hardware co-design, ensuring efficient large-scale deployment of LLMs and vision models.
This role offers a unique opportunity to shape the future of LLM inference infrastructure, ensuring scalable, high-performance AI deployment across a diverse range of applications. If you're passionate about pushing the boundaries of AI inference, we’d love to hear from you!
Responsibilities
Inference Framework Development and Optimization
- Design and develop fault-tolerant, high-concurrency distributed inference engine for text, image, and multimodal generation models.
- Implement and optimize distributed inference strategies, including Mixture of Experts (MoE) parallelism, tensor parallelism, pipeline parallelism for high-performance serving.
- Apply CUDA graph optimizations, TensorRT/TRT-LLM graph optimizations, and PyTorch-based compilation (torch.compile), and speculative decoding to enhance efficiency and scalability.
Software-Hardware Co-Design and AI Infrastructure
- Collaborate with hardware teams on performance bottleneck analysis, co-optimize inference performance for GPUs, TPUs, or custom accelerators.