Skip to content
Crusoe

Senior Cloud Support Engineer - Managed Inference

Denver, CO - USOnsite · United States
Senior · FullTime · Cloud Go-To-Market (GTM)
POSTED 14 OCTVERIFIED 59M AGO
Apply Ask
Role
39 days opentrue age
Closes in ~25d at the median (64d)
Posted 14 Oct · n=102
Pay
$188k–$190kno pay posted
$136k$280k
Market p25–p75
$136k–$176k
Crusoe p25–p75
$188k–$190kn=3
H-1B median · Software engineering
$280k
Denver · n=106 · 365d to 19 Nov
CompanyCrusoe →
316open roles
Opened · 30d
+65
Closed · 30d
−89
Signal
● Steady−24 net
20d of snapshots · 30d window
Market
17,046open · Senior Software engineering
Opened · 7d
+1,3348% of open
All software engineering
75,000open
All tracked boards · live 22 Nov · n=17,046
Visa
13H-1B LCAs · FY26
Median wage
$235k
LCAs FY26 · n=13 · to 2026-06-30
PythonGoKubernetesDockerLLMsDistributed systems

Crusoe is on a mission to accelerate the abundance of energy and intelligence. As the only vertically integrated AI infrastructure company built from the ground up, we own and operate each layer of the stack — from electrons to tokens — to power the world's most ambitious AI workloads. When you join Crusoe, you join a team that is building the future, faster.

We're in the midst of the greatest industrial revolution of our time. The demand for AI compute is boundless, and power is a bottleneck. We're solving that — with an energy-first approach that makes AI infrastructure better for the world and faster for the people innovating with AI.

We're looking for problem-solving, opportunity-finding teammates with a sense of urgency, who believe in the scale of our ambition and thrive on a path not fully paved — people who want to grow their careers alongside a team of experts across energy, manufacturing, data center construction, and cloud services.

If you want to do the most meaningful work of your career, help our customers and partners advance their AI strategies, and be part of a high-performing team that believes in each other, come build with us at Crusoe.

About the Role

Crusoe is looking for a Senior Support Engineer to be the technical front line for customers building on Crusoe Managed Inference, our serverless AI inference service powered by MemoryAlloy™ cluster-native KV caching. You’ll work directly with AI developers and enterprise customers running production inference workloads — from agentic applications to large-context, long-form generation — helping them deploy, troubleshoot, and optimize their use of the platform. This is a high-visibility role that bridges customer success, infrastructure engineering, and product feedback loops.

What You’ll Do

Serve as the primary technical escalation point for customer issues related to Managed Inference: latency, throughput, token pricing/billing, API errors, model availability, and autoscaling behavior.

Diagnose and resolve issues spanning the inference stack — GPU cluster scheduling, KV cache behavior (MemoryAlloy), prefix caching/routing, and model-serving endpoints.

Support customers using both pre-configured open-source models and Bring Your Own Model (BYOM) deployments.

Guide customers through onboarding via the Crusoe Intelligence Foundry.

Reproduce reported issues in staging/test environments; write clear, reproducible bug reports for engineering.

Monitor production health dashboards; proactively flag degraded performance before customers notice.

Own and maintain internal runbooks, troubleshooting guides, and customer-facing documentation/FAQs.

Partner with Product and Engineering to relay customer pain points and feature requests.

Participate in an on-call rotation for production incidents affecting managed endpoints; drive incident communication and post-mortems.

Help attain SLA compliance metrics for enterprise customers.

Create knowledge base articles and deliver technical training.

What We’re Looking For

5+ years in a technical support, solutions engineering, SRE, or DevOps role, ideally supporting infrastructure, cloud, or ML/AI platforms.

Strong understanding of LLM inference concepts: tokens, context windows, KV caching, batching, and latency/throughput tradeoffs, including TTFT, TPOT, and tokens/sec.

Solid serving-stack fundamentals: request routing, replica health and failover, autoscaling, and latency/throughput analysis using percentile metrics (p50/p90/p99).

Hands-on experience with GPU-based infrastructure, container orchestration (Kubernetes), and distributed systems debugging.

Proficiency with API-based services (REST, gRPC) and comfort reading logs/traces across a distributed inference pipeline.

Scripting/programming ability (Python, Go, or Bash) for diagnostics and tooling.

Excellent written and verbal communication skills — you’ll explain complex infrastructure issues to both engineers and non-technical stakeholders.

Customer-first mindset with the judgment to balance empathy, urgency, and technical accuracy.

Source · CrusoeFirst seen 2 Nov1 editsOriginal ↗