Forward Deployed Engineer, Inference
Core
Architect high-performance, resilient machine learning systems for large language models within strategic enterprise environments and custom infrastructure.
Role type
Staff Forward Deployed Engineer (FDE)
Builds
Multi-tenant model serving, cross-datacenter failover strategies, and optimized private deployments for enterprise customers.
Domain
Enterprise AI / Large Language Model Inference / Distributed Systems
Deliverable
production ML models
Required skills
Production Kubernetes orchestration, LLM inference dynamics, modern inference engines (vLLM, TensorRT-LLM), distributed serving techniques, Python/Go/C++ programming, customer-facing technical leadership.
Preferred skills
Experience with next-generation accelerators (GPUs, TPUs, AMD, custom ASICs), multi-cluster scale management.
Technologies
Kubernetes, GCP, Azure, AWS, OCI, vLLM, TensorRT-LLM, Python, Go, C++
Responsibilities
Embed with customer engineering teams to architect connective tissue between AI models and live production environments; Design advanced model serving topologies and intelligent routing; Optimize 'AI-in-a-box' and private deployments; Conduct rigorous benchmarking and profiling of customer LLM workloads; Accelerate hardware validation on next-generation accelerators; Translate field friction into platform upgrades; Ensure Day-1 production reliability and observability frameworks.
Seniority
Staff, hands-on IC
