Crusoe designs, builds, and operates energy-first AI infrastructure. Its offerings include Crusoe Cloud for GPU-based training, fine-tuning, inference, and managed services, alongside AI-optimized data centers and energy infrastructure.

View jobs by Crusoe, Inc.

Skills

Autoscaling Docker Dpo Fine-Tuning Gpu Inference Kubernetes Kv Cache Lora Profiling Quantization Sft Sglang Tensorrt-Llm Vllm

Candidate Availability

Onsite · Tel Aviv · Required

Required and preferred rules are kept separate and reflect the wording in the original posting.

About the Role

You will partner directly with strategic customers to deploy, optimize and scale their models into production, owning the journey from benchmark POCs to production endpoints. You will tune inference engines, diagnose bottlenecks, lead technical discussions, handle onboarding, autoscaling and capacity planning, and publish technical content.

Requirements

5+ years in a technical role with strong programming and production skills (Kubernetes, Docker, GPU servers)
Proven ability to lead technical discussions with customer engineers and leadership
Hands-on experience with inference engines (vLLM, SGLang, TensorRT-LLM) and performance profiling
Strong command of KV-cache tuning, batching, parallelism, quantization and cost math
Solid knowledge of the open-source model landscape and hardware-model matching
Experience as an FDE, solutions engineer or inference engineer at an AI cloud, lab or provider
Hands-on background in fine-tuning/post-training (LoRA, SFT, DPO) or open-source engine contributions

Responsibilities

Scope workloads, define metrics (TTFT, throughput, cost/token), build benchmarks and lead technical POCs
Serve as technical lead for customer engineering teams through architecture reviews and rollout planning
Tune engines (KV cache, speculative decoding, parallelism, quantization) to hit performance targets
Profile and diagnose engine-level bottlenecks and deliver production fixes
Own customer onboarding, deployment, autoscaling, capacity planning and SLO monitoring
Optimize configurations for base, custom and fine-tuned models
Feed field insights into product roadmaps and contribute code to the inference engine and tooling
Publish reference architectures, cookbooks and technical blogs

Benefits

Competitive benefits package tailored to local market standards
Pension contributions