Senior LLM Inference Engineer - End-to-End, Equity

Entrada Ventures; Santa Clara (CA); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Competitive compensation

Equity opportunities

Benefits in Santa Clara, CA

Job summary

d-Matrix Frontier Group in Santa Clara, CA is seeking end-to-end inference engineers to drive novel ideas to deployed, optimized systems across the inference stack. You will work from kernel-level optimization to distributed orchestration and high-level serving APIs, shaping the future of AI silicon usage.

Ideal candidates have deep experience with LLM inference, open-source frameworks, and heterogeneous hardware deployments, delivering POCs to customers and contributing to open-source projects.

Qualifications

• Bachelors with 10+ years of relevant engineering experience or equivalent.
• Masters/PhD with 6+ years of relevant industry experience preferred.
• Strong Python and C/C++ proficiency.
• Hands-on experience optimizing LLM inference and related kernels.
• Experience with major inference frameworks at contributor level.
• Familiarity with GPU kernel programming and profiling tools.

Responsibilities

• Identify and prototype emerging LLM inference use cases for heterogeneous hardware.
• Build POCs demonstrating D-Matrix capabilities to customers and partners.
• Develop and tune custom kernels and operator-level optimizations for throughput and latency.
• Drive quantization, sparsity, and batching strategies for the computational model.
• Build and maintain inference runtimes, serving frameworks, and evaluation tooling.
• Contribute to distributed inference systems and work with hardware teams.

Skills

Python

C/C++

LLM inference

CUDA/Triton

Performance profiling

Education

Bachelor's degree in CS/EE

Master's or PhD in CS/EE

Tools

vLLM

SGLang

TensorRT-LLM

ONNX Runtime

Job description

d-Matrix Frontier Group in Santa Clara, CA is seeking end-to-end inference engineers to drive novel ideas to deployed, optimized systems across the inference stack. You will work from kernel-level optimization to distributed orchestration and high-level serving APIs, shaping the future of AI silicon usage.

Ideal candidates have deep experience with LLM inference, open-source frameworks, and heterogeneous hardware deployments, delivering POCs to customers and contributing to open-source projects.