Forward Deployed Inference Engineer

About the role

The Forward Deployed Inference Engineer will bridge the gap between customer needs and Tensordyne's AI inference platform. This role involves optimizing generative AI models for high-performance hardware, managing technical customer deployments, and collaborating with internal engineering teams to improve system capabilities.

Responsibilities

• Turn customer workloads into fast, credible performance answers through profiling and benchmarking.
• Convert and bring up customer models on the Tensordyne stack, validate numerical quality, and identify performance bottlenecks.
• Work directly with customers and partners on technical PoCs, integration, deployment, and debugging.
• Track profiling-to-hardware accuracy by comparing simulation results with actual hardware deployments.
• Turn repeated customer-specific learnings into reusable tooling, documentation, benchmarks, or product improvements.

Required skills

• AI models
• Inference systems
• LLMs
• Python
• PyTorch
• Profiling
• Benchmarking
• Model optimization

Nice to have

• vLLM
• SGLang
• Customer-facing
• Hardware acceleration
• Quantization
• Distributed inference
• Kubernetes
• Rust

About the Company

Tensordyne is building a new class of AI inference system designed for high-performance, power-efficient deployment of the world’s most demanding generative AI workloads. Their platform integrates purpose-built silicon, new AI math, and optimized networking for large-scale AI inference.