ML Infrastructure Engineer
Core
Design, build, and scale inference and model-serving infrastructure for AI agents to ensure reliable, high-concurrency production performance.
Role type
ML Infrastructure Engineer
Builds
Inference and model-serving platforms for AI agents
Domain
Enterprise AI, regulated industries (insurance, banking, healthcare, asset management)
Deliverable
production ML models
Required skills
ML inference system design, model-serving platforms, distributed systems, containerization, orchestration, monitoring, observability, cloud deployment, systems/backend programming
Preferred skills
knowledge graphs, semantic search, graph databases, real-time inference, agentic AI pipelines, enterprise data integration
Technologies
TensorFlow Serving, TorchServe, Triton, KServe, Docker, Kubernetes, Prometheus, Grafana, AWS, GCP, Azure, Python, Go, Rust, C++, Java
Responsibilities
Design and scale inference-serving systems from ground up, optimize systems for latency and throughput, collaborate with ML teams on integration, drive solutions for infrastructure challenges
Seniority
Mid-Senior, hands-on IC
