> Markdown version of [/jobs/ext/3744157-software-engineer](https://www.wearedevelopers.com/jobs/ext/3744157-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Software Engineer

- **Company:** Pulse LLC
- **Location:** San Francisco, CA, United States
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** C++ (Programming Language), Nvidia CUDA, Python (Programming Language), Machine Learning Operations, TensorRT
- **Published:** October 15, 2026
- **Apply:** https://startup.jobs/software-engineer-inference-pulse-10442856

## About the Role

* Eager to learn and adapt quickly
 * Prior startup or founding experience is a plus

What we are looking for

 * 5 days in-office at our San Francisco office
 * Eager to learn and adapt quickly
 * Prior startup or founding experience is a plus, * 3+ years in performance engineering or ML systems
 * Strong Python, plus C++ or CUDA exposure
 * Experience with GPU profiling and model serving

Nice to have

 * Experience reducing p95 and cost in production ML systems

## Description

Specialize in low-latency, high-throughput inference for OCR and multimodal models. Own profiling, batching, and autoscaling across single-tenant and multi-tenant environments., * Build inference services with smart batching and caching

 * Optimize kernels, tokenization, and model graphs
 * Evaluate vLLM, TensorRT LLM, and Triton tradeoffs
 * Implement autoscaling and admission control with clear SLOs
 * Own performance dashboards and capacity planning