Senior AI/ML Systems Architect - Edge & On-Prem

Lattice Semiconductor; San Jose (CA); On-site; USD 200,000 - 260,000; Full time

Job summary

Lattice Semiconductor in San Jose, CA is seeking a Sr. Staff Engineer to lead AI/ML initiatives across on‑prem and edge deployments.

You will design, train, and optimize models, build scalable pipelines, and collaborate with software, infra, and domain teams to deliver production quality solutions. The role requires deep expertise in LLMs, model optimization, and multi‑agent AI, plus strong Python and ML framework experience.

Qualifications

• Master’s/Ph.D. in CS/Engineering or equivalent experience.
• 8+ years in AI/ML with 3+ years on LLMs and large-scale models.
• Hands-on with LLMs and open-weight models.
• Proficiency in Python and ML frameworks (PyTorch, TensorFlow).
• Experience with vector databases and retrieval models.

Responsibilities

• Train, fine-tune, and evaluate ML models including LLMs.
• Optimize models for local inference via quantization and pruning.
• Deploy models on-prem or at edge using PyTorch, TensorRT, ONNX.
• Build scalable training/inference pipelines for reproducibility.
• Integrate models into production via APIs and services.
• Monitor performance, latency, and resource usage in production.
• Collaborate with engineers, infra, and domain experts.
• Ensure security, privacy, and compliance for restricted environments.
• Document architectures, training procedures, and workflows.

Skills

ML model fine-tuning

Model deployment

Python

PyTorch

LLMs

Quantization

Inference optimization

Vector databases

Multi-agent AI

Documentation

Education

Master's/Ph.D. in CS/Engineering

Tools

PyTorch

TensorRT

ONNX

vLLM

llama.cpp

Docker

Linux

FAISS

Weaviate

Chroma

Pinecone

Milvus

Job description

Lattice Semiconductor in San Jose, CA is seeking a Sr. Staff Engineer to lead AI/ML initiatives across on‑prem and edge deployments.

You will design, train, and optimize models, build scalable pipelines, and collaborate with software, infra, and domain teams to deliver production quality solutions. The role requires deep expertise in LLMs, model optimization, and multi‑agent AI, plus strong Python and ML framework experience.