SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Tensordyne is building a new class of AI inference system designed for high-performance, power-efficient deployment of demanding generative AI workloads. The platform combines purpose-built silicon, optimized AI math, scale-up networking, and memory architecture into a tightly integrated system for large-scale AI inference, serving hyperscalers, frontier model developers, enterprises, and infrastructure partners.
As the company moves from system development into silicon bring-up, customer validation, beta deployments, and production rollout, it is building a technical customer organization that bridges engineering teams and deploying companies.
The Forward Deployed Inference Engineer combines deep AI systems expertise with strong customer instincts. You will own the path from a customer workload or model request to a technical result—optimized models running successfully on Tensordyne hardware and software. The role sits at the intersection of model architecture, inference performance, systems optimization, developer tooling, and customer deployment, working hands-on with engineering while acting as a technical bridge to Product, BizDev, Sales, and customers.
Key responsibilities:
- Turn customer workloads into fast, credible performance answers through profiling and benchmarking. Define relevant KPIs, compare against competitive baselines, and keep evaluation methodology current with external benchmarks.
- Model enablement and optimization: convert and bring up customer models on the Tensordyne stack, validate numerical quality, identify performance bottlenecks, and work with compiler, runtime, kernel, and system teams to improve results.
- Deployment and forward engineering: work directly with customers and partners on technical PoCs, integration, deployment, and debugging; translate requirements into measurable acceptance criteria for quality, latency, throughput, and other KPIs.
- Track profiling-to-hardware accuracy by continuously comparing profiling/simulation results with actual hardware deployments, explain material gaps, and flag missing capabilities in compiler, SDK, inference server, KV-cache management, or adjacent systems.
- Turn repeated customer-specific learnings into reusable tooling, documentation, benchmarks, or product improvements.
REQUIREMENTS:
- Strong hands-on experience with AI models and inference systems, especially dense and MoE LLMs (Llama, DeepSeek, Qwen, GPT-OSS, Kimi, GLM), and VLM, speech, and diffusion models.
- Strong Python and PyTorch skills and the ability to understand and modify model code.
- Experience profiling, benchmarking, or optimizing model inference and reasoning about latency, throughput, memory, and utilization.
- Strong problem-solving and communication skills, with the ability to drive ambiguous technical problems across team boundaries.
- Proficiency in using AI-powered developer tools (e.g., Claude Code, Cursor).
STRONG PLUSES:
- Experience with LLM serving and deployment stacks such as vLLM, SGLang, or similar systems.
- Experience working directly with customers or external technical partners.
- Experience bringing models up on new accelerators or non-standard hardware, including performance debugging across framework/runtime/hardware boundaries.
- Practical experience with production inference techniques or environments such as quantization, distributed inference, or Kubernetes.
- Experience navigating and contributing to Rust codebases.
