Senior AI Systems Engineer - LLMs, Edge & On-Prem

Lattice Semiconductor Corp; Nellis Air Force Base Census-Designated Place (NV); On-site; USD 199,000 - 243,000; Full time

Benefits offered by this job

Equity compensation

Healthcare and retirement plans

Paid time off

Job summary

Lattice Semiconductor Corp is seeking a Sr. Staff Engineer to join our AI/ML team.

You will train, fine-tune, and evaluate ML models, optimize for local inference, and deploy on-prem or at the edge, leveraging frameworks such as PyTorch, TensorRT, ONNX, vLLM, or llama.cpp. Collaborate with software and infra teams to deliver end-to-end AI solutions, document architectures, ensure security and compliance, and mentor engineers.

Qualifications

• Advanced degree or equivalent practical experience in AI/ML.
• 8+ years in AI/ML with LLMs, code generation, or large-scale neural networks.
• Hands-on experience with LLMs and open-weight models.
• Proficiency in Python and ML frameworks (PyTorch/TensorFlow).
• Experience deploying models in local/on-prem/restricted environments.

Responsibilities

• Train, fine-tune, and evaluate ML models including LLMs.
• Optimize models for local inference via quantization/pruning/distillation.
• Deploy models on-prem or at the edge using PyTorch/TensorRT/ONNX/vLLM/llama.cpp.
• Build and maintain training/inference pipelines for reproducibility and scalability.
• Integrate locally deployed models into production systems via APIs.
• Monitor model performance, latency, and resource usage in production.
• Collaborate with software/infrastructure/domain experts for end-to-end AI solutions.
• Ensure security, privacy, and compliance in restricted/offline environments.
• Document model architectures, training procedures, and deployment workflows.

Skills

Python

LLMs

Multi-agent AI

Model optimization

KPIs definition

AI deployment

Security & privacy

Education

PhD or MS in CS/Engineering

8+ years AI/ML experience

Tools

PyTorch

TensorFlow

ONNX

Docker

FAISS/Weaviate/Pinecone

Llama.cpp

LangGraph/CrewAI

Job description

Lattice Semiconductor Corp is seeking a Sr. Staff Engineer to join our AI/ML team.

You will train, fine-tune, and evaluate ML models, optimize for local inference, and deploy on-prem or at the edge, leveraging frameworks such as PyTorch, TensorRT, ONNX, vLLM, or llama.cpp. Collaborate with software and infra teams to deliver end-to-end AI solutions, document architectures, ensure security and compliance, and mentor engineers.