Machine Learning Engineer
Core
Design and build the high-level architecture of a next-generation MLOps platform for deploying, scaling, and monitoring GenAI models (LLMs, speech, vision, diffusion) across cloud and on-prem environments.
Role type
Senior IC Machine Learning Engineer (MLOps Infrastructure)
Builds
Scalable, reliable, GPU-accelerated ML workflows and MLOps infrastructure for a GenAI inference platform.
Domain
Generative AI, Cloud Infrastructure, Distributed Systems
Deliverable
infrastructure
Required skills
System design, Distributed systems, GPU-based ML workloads, Software engineering fundamentals, Infrastructure-as-code, Cloud platforms, ML fundamentals, Multi-step pipeline orchestration, Linux internals, Networking, Performance tuning
Preferred skills
Modern inference stacks (TensorRT, Triton, vLLM/TGI, SGLang), Model optimization, CUDA concepts, LLM/VLM/ASR pipeline experience, CI/CD, Docker, High-availability system design
Technologies
Terraform, Ansible, AWS, GCP, Azure, Linux, Docker, GitHub workflows
Responsibilities
Design and implement core architecture for GPU-accelerated workloads at scale, Formalize heterogeneous ML workloads and build orchestration abstractions, Build internal systems for continuous deployment across multi-cloud environments, Create frameworks for reliability and observability, Develop internal tooling for benchmarking and model deployment, Troubleshoot complex systems and distributed workloads
Seniority
Senior, hands-on IC
