Deskripsi Pekerjaan
Synthetix Labs is seeking an exceptional Senior AI Platform Engineer to design, scale, and optimize our next-generation machine learning infrastructure in San Francisco. In this role, you will build robust distributed compute engines and low-latency inference pipelines supporting enterprise-grade foundation models.
We prioritize engineering simplicity, high reliability, and measurable performance. You will collaborate directly with our research and systems teams to translate model breakthroughs into resilient production services serving millions of downstream queries daily.
Tanggung Jawab
- Architect, deploy, and maintain high-throughput, low-latency LLM inference pipelines using Triton and vLLM.
- Build scalable distributed training infrastructure using Ray and Kubernetes on multi-node GPU clusters.
- Optimize hardware utilization, cluster throughput, and resource allocation across hybrid cloud environments.
- Automate orchestration, telemetry, model benchmarking, and continuous delivery workflows for ML artifacts.
- Collaborate with security and product teams to enforce zero-trust access controls and data isolation across model boundaries.
- Diagnose performance bottlenecks across kernel, network, memory, and application layers to minimize compute overhead.
Kualifikasi
- Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or equivalent practical experience.
- 5+ years of software engineering experience with deep expertise in Python, Go, or C++.
- 3+ years operating production ML infrastructure, model serving engines, or large-scale distributed systems.
- Hands-on experience with Kubernetes, GPU orchestration (NVIDIA CUDA), and infrastructure-as-code tools (Terraform).
- Proven proficiency profiling system performance and tuning distributed networking protocols (gRPC, NCCL).
- Demonstrated track record of delivering fault-tolerant cloud-native services in AWS, GCP, or bare-metal setups.