1 month ago
Base Salary
$183k - $261k/yr
Responsibilities
- Build and optimize the model inference path through quantization, KV-cache optimization, batching, and latency, memory, and throughput tuning on constrained commodity hardware.
- Fine-tune and evaluate models for bounded tasks and build evaluation harnesses that gate releases based on accuracy, latency, and security relevance.
- Design and expand the task-execution runtime for bounded sub-agents, including dynamic task generation and context compaction.
- Drive hardware acceleration and sparsity support and enable larger models as the platform matures.
- Partner with systems and backend engineers to ship capabilities end-to-end and iterate using production signals from Netskope’s customer base.
Requirements
- 10+ years of overall industry experience, including 4+ years of hands-on ML/AI experience in model development, fine-tuning, and inference optimization.
- Hands-on experience with fine-tuning methods such as LoRA and QLoRA, quantization formats or methods including GGUF, AWQ, and GPTQ, and inference runtimes such as vLLM, SGLang, TensorRT-LLM, ONNX Runtime, llama.cpp, or MLX/CoreML.
- Strong Python skills; C++ experience for low-level interoperability is a plus.
- Strong understanding of transformer internals, KV cache, attention, batching, memory footprint, and inference performance and cost optimization.
- Experience with on-device or edge inference is a strong plus.
- Fluency with agentic coding systems and curiosity or experience with agent harnesses such as Claude Code, Pi, and Codex.
- MS in Computer Science, Machine Learning, Electrical Engineering, or an equivalent technical degree with a focus in AI/ML research is required.
- PhD in a related field is strongly preferred.
- Clear communication and ability to explain model or infrastructure bottlenecks to cross-functional teammates.
Benefits
- Competitive total rewards package with potential bonus plan and stock award program.
- Comprehensive health plan and other benefits may be available.
- Role is available at Senior Staff and above, with individual leveling based on skills and background.
- Position is covered by a national salary range for candidates in multiple U.S. states.
Categories
About Netskope
Netskope (NASDAQ: NTSK), a leader in modern security and networking for the cloud and AI era, addresses the needs of both security and networking teams by providing optimized access and real-time, context-based security for the AI ecosystem inclusive of agents, applications, tools, LLMs, people, devices, and data. Thousands of customers, including more than 30 of the Fortune 100, trust the Netskope One platform, its Zero Trust Engine, and its powerful NewEdge network to reduce risk and gain full visibility and control over cloud, AI, SaaS, web, and private applications – providing security and accelerating performance without trade-offs.