SambaNova Systems
Forward Deployment Engineer
About this role
SambaNova seeks a Forward Deployment Engineer to embed with enterprise customers, architecting and deploying generative AI applications on their SN40L platform and SambaStack infrastructure. You'll optimize inference performance, troubleshoot production issues across the full stack, and translate customer needs into product requirements while serving as a technical liaison between the field and engineering teams.
What you'll do
- Embed with strategic customers to design, build, and deploy production GenAI applications on SambaNova hardware and SambaStack
- Architect and implement LLM workflows including RAG pipelines, multi-agent systems, fine-tuning, and custom coding solutions
- Optimize AI inference performance, benchmark model throughput/latency/accuracy against requirements and competitors
- Troubleshoot and resolve production issues end-to-end across model, software, and hardware layers
- Translate customer needs into product requirements and engineering feedback; represent field reality to internal teams
- Develop reusable accelerators, reference architectures, and playbooks to scale learnings across deployments
What they're looking for
- Python programming
- Generative AI application development (LLM orchestration, RAG, agentic frameworks)
- Machine learning fundamentals (training, fine-tuning, inference optimization, quantization)
- Cloud infrastructure deployment (AWS, Azure, GCP)
- Kubernetes and Docker containerization
- MLOps tooling and practices
- C++ or CUDA (strongly preferred)
- Customer engagement and technical communication
Opens the official application on the employer’s site. No login required.
SambaNova Systems
SambaNova Systems builds AI inference and machine learning platforms with specialized compiler infrastructure and runtime optimization. The company is hiring for compiler engineers, software engineers, runtime engineers, and ML solutions engineers to enhance its AI platform capabilities, as well as process and quality engineers for manufacturing excellence.
- Website
- sambanova.ai
Likely interview questions
- Walk us through a production GenAI system you deployed—how did you optimize inference performance and what trade-offs did you navigate?
- Describe your experience implementing RAG pipelines or multi-agent systems. How did you handle retrieval quality and latency constraints?