ML Systems, LLM Post-Training

ChipAgents • San Jose, CA

3d • $150,000 - $350,000

About The Position

We are seeking an ML Systems Engineer to optimize the performance and efficiency of large language model inference powering our agentic AI platform. This is a technical role focused on low-level systems optimization. You will implement performance optimizations, build evaluation harnesses, and architect multi-node clusters for training and inference that push the limits of LLM throughput and latency. Your work will directly impact the responsiveness and cost-efficiency of AI agents used by leading semiconductor companies to design chips.

Requirements

• B.S., M.S., or PhD in Computer Science, Electrical Engineering, or a related field, or equivalent experience.
• Experience with large-scale ML systems, GPU computing, or high-performance inference optimization.
• Strong proficiency in Python and C++/CUDA.
• Hands-on experience with SGLang, vLLM, PyTorch, or similar inference frameworks.
• Deep understanding of GPU architecture, memory hierarchies, and parallel computing paradigms.
• Experience deploying and optimizing LLMs in production, including model serving, batching strategies, distributed inference, or quantization.
• Strong systems-level debugging and profiling skills, with comfort working across multiple layers of the stack from CUDA kernels to application logic.
• Self-directed problem solver interested in ambitious optimization challenges.

Nice To Haves

• Familiarity with distributed computing frameworks such as Ray and multi-node training or inference.

Responsibilities

• Design, deploy, and optimize LLM inference systems across multi-node clusters, maximizing throughput and minimizing latency for production workloads.
• Implement and benchmark concrete inference optimizations.
• Profile and analyze inference bottlenecks at the systems level, from GPU kernel execution to memory bandwidth constraints.
• Build evaluation harnesses and benchmarking frameworks to measure accuracy, throughput, latency, and resource utilization across parallelism strategies.
• Collaborate with research scientists to integrate new model architectures and optimizations into production inference infrastructure.
• Investigate and apply emerging techniques from research papers and open-source projects to improve inference performance.

Benefits

• Unlimited PTO.
• Medical, vision, and dental benefits.
• 401(k).
• Equity.
• Engineering-centric offices with free parking, a private gym, and free lunch, drinks, and snacks.
• Access to substantial GPU compute resources for experimentation and benchmarking.

What This Job Offers

• Job Type: Full-time