Lead Software Engineer building real-time observability and root-cause analysis for Baseten's large-scale GPU fabrics and high-performance networks. Requires strong distributed systems and infrastructure experience to correlate telemetry from switches, NICs, GPUs, and inference services.
200k – 380k
Hybrid7+ YOEDevOps / SRE
About the role
Responsibilities
Own Baseten’s GPU fabric observability and root-cause analysis architecture.
Build telemetry pipelines across switches, NICs, hosts, GPUs, Kubernetes, and inference services.
Model topology, flow paths, service ownership, and failure domains.
Separate true fabric faults from host, NIC, GPU, kernel, driver, RDMA, scheduler, and workload failures.
Create clear operator workflows for triage, remediation, and post-incident learning.
Example Initiatives
Real-time telemetry engine — Build the ingestion, reduction, storage, and query path for high-cardinality fabric, host, GPU, and workload telemetry.
Service-aware fabric diagnosis — Build collectors, probes, and topology-aware correlation to detect latency, drops, stalls, congestion, bad paths, and degradation.
Software-aware RDMA diagnosis — Tie network behavior to RDMA operations, GPUDirect paths, KV cache transfers, prefill/decode disaggregation, and request latency.
Requirements
Staff-level or senior staff-level experience building production infrastructure software.
Strong distributed systems background, especially streaming systems, telemetry pipelines, diagnostics, or control-plane software.
Experience building systems that process high-volume, high-cardinality, noisy operational data.
Understanding of networking fundamentals and high-performance networks.
Ability to work with low-level infrastructure signals and build practical correlation, anomaly detection, or root-cause analysis systems.
Nice-to-Haves
Experience with RDMA data paths, GPUDirect transfers, prefill/decode disaggregation, KV cache movement, request routing, and workload backpressure.
Familiarity with RoCE, InfiniBand, ECN/DCQCN, RNIC, GPU drivers, and related technologies.
Benefits
Competitive compensation, including meaningful equity.
100% coverage of medical, dental, and vision insurance for employee and dependents.
Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!).
Paid parental leave.
Fertility and family-building stipend through Carrot.
Company-facilitated 401(k).
Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.
Skills
Distributed SystemsTelemetry PipelinesStreaming SystemsHigh-Cardinality DataAnomaly DetectionRoot Cause AnalysisNetworkingRdmaGpudirectKubernetesInfiniBandRoce
Build and operate scalable cloud infrastructure platforms, abstractions, and enterprise deployments for Decagon's agentic AI systems. Requires 4+ years in infrastructure/DevOps, deep expertise in Kubernetes, Terraform, major cloud providers, networking, and production reliability (monitoring, on-call).
200k – 400k
On-site7+ YOEDevOps / SRE
Senior Software Engineer, Observability
Together AISan Francisco, CA
Senior Software Engineer building scalable observability platforms (metrics, logs, traces) with Prometheus, Grafana, OpenTelemetry and related tools for Together AI's GPU cloud infrastructure. Requires strong distributed systems and infrastructure-as-code experience.
200k – 280k
On-site5+ YOEDevOps / SRE
Senior Software Engineer, Accelerated Delivery
SnowflakeMenlo Park, CA
Build and evolve continuous deployment, progressive delivery, and AI-augmented release platforms for safe, large-scale multi-cloud rollouts on Kubernetes at Snowflake. Requires strong systems programming (Golang/Java/C++), Kubernetes, observability, and DevOps experience.
200k – 288k
Hybrid5+ YOEDevOps / SRE
Senior Software Engineer - Snowpark Container Service
SnowflakeBellevue, WA +1
Senior engineer to design, build, and lead development of Snowpark Container Services, a Kubernetes-based container compute platform. Requires 7+ years building large-scale distributed systems and strong coding skills in Java, C++, or Go.
200k – 288k
Hybrid7+ YOEDevOps / SRE
Lead Site Reliability Engineer
StuutSan Francisco, CA
Lead SRE driving reliability strategy, infrastructure architecture, observability, and incident response for a B2B fintech platform on AWS and Kubernetes. Requires 7+ years building production-grade distributed systems.