Senior Backend Engineer, Inference Platform
$200k - $290k • Remote • San Francisco
Posted 1mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Infrastructure Engineer
About the job
Together AI is building the Inference Platform to deliver advanced generative AI models, powering multi-tenant serverless workloads and dedicated endpoints. This platform enables developers, enterprises, and researchers to utilize the latest LLMs and multimodal models at scale. The role focuses on optimizing latency and maximizing the utilization of tens of thousands of GPUs. You will collaborate directly with research teams to productionize frontier models and engage with the open-source community, contributing to and leveraging projects like SGLang and vLLM to enhance inference performance and efficiency.
Responsibilities
- Build and optimize global and local request routing for low-latency load balancing.
- Develop auto-scaling systems for dynamic resource allocation and meeting strict SLOs.
- Design systems for multi-tenant traffic shaping, including rate limiting and regulation.
- Engineer trade-offs between latency and throughput for efficient workload serving.
- Optimize prefix caching to reduce model compute and speed up responses.
- Collaborate with ML researchers to bring new model architectures into production at scale.
- Continuously profile and analyze system performance to identify and implement optimizations.
Requirements
- 5+ years of experience building large-scale, fault-tolerant, distributed systems and API microservices.
- Strong background in designing, analyzing, and improving efficiency, scalability, and stability of complex systems.
- Excellent understanding of low-level OS concepts: multi-threading, memory management, networking, and storage performance.
- Expert-level programming in Rust, Go, Python, or TypeScript.
- Knowledge of modern LLMs and generative models and their production serving is a plus.
- Experience with the open-source inference ecosystem (e.g., SGLang, vLLM, NVIDIA Dynamo) is highly valuable.
- Experience with Kubernetes or container orchestration is a strong plus.
- Familiarity with GPU software stacks (CUDA, Triton, NCCL) and HPC technologies (InfiniBand, NVLink, MPI) is a plus.
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or related field, or equivalent practical experience.
Benefits
- Competitive compensation
- Startup equity
- Health insurance
- Other competitive benefits