Senior AI Platform Architect - Generative AI

Lattice Semiconductor; San Jose (CA); On-site; USD 199,000 - 243,000; Full time

Job summary

Lattice Semiconductor is seeking a Sr. Staff Engineer to join our AI/ML team in the U.S. and help design enterprise-wide Generative AI solutions.

You will architect AI gateways, enable routing across multiple LLMs, and drive cost-saving strategies while mentoring engineers and aligning with governance and security standards. The role emphasizes hands-on development, collaboration with security/compliance, and leadership in deploying scalable AI models and retrieval pipelines using cloud-based

Qualifications

• Enterprise-scale generative AI architecture experience.
• Experience integrating cutting-edge LLMs and autonomous AI agents.
• Develop RAG pipelines for knowledge retrieval and context-aware responses.
• Build and optimize agentic AI systems interacting with APIs, databases, and IDEs.
• Fine-tune LLMs for domain-specific applications.
• Optimize models for local inference (quantization, pruning, distillation).
• Deploy models on-prem or at the edge with PyTorch, TensorRT, ONNX.
• Build training and inference pipelines for reproducibility.
• Integrate locally deployed models into production via APIs.
• Monitor performance, latency, resource utilization.
• Design AI gateway solutions and model routing techniques.
• Proven cost savings using local/open-source models or optimizations.
• Understanding of LLM provider ecosystems and multi-model orchestration.
• Experience with cloud infrastructure and enterprise architecture frameworks.
• Knowledge of AI governance, security, compliance in enterprises.
• Excellent communication with both technical and non-technical stakeholders.
• Deploy scalable AI models and retrieval pipelines using cloud-based MLOps (AWS/GCP/Azure, Docker, Kubernetes).
• Optimize LLMs for real-time inferencing.

Responsibilities

• Design and architect enterprise-wide Generative AI solutions, including reference architectures and standards.
• Design, build, and maintain an enterprise AI gateway for access governance.
• Develop routing to direct requests across multiple LLMs and providers.
• Evaluate local/on-prem models to reduce costs.
• Establish frameworks to measure cost savings from routing and infra choices.
• Collaborate with engineering, security, and compliance teams.
• Define best practices for prompt orchestration, caching, and fallbacks.
• Provide technical leadership to AI/ML engineers.
• Lead a team of AI/ML engineers.

Skills

Generative AI architecture

LLM integration

RAG pipelines

API integration

Cost optimization

Edge/local inference

Cloud/MLOps

AI governance & security

Team leadership

Education

Master's or PhD in CS/AI

Tools

LangChain

OpenAI APIs

PyTorch

TensorRT

ONNX

vLLM

llama.cpp

Job description

Lattice Semiconductor is seeking a Sr. Staff Engineer to join our AI/ML team in the U.S. and help design enterprise-wide Generative AI solutions.

You will architect AI gateways, enable routing across multiple LLMs, and drive cost-saving strategies while mentoring engineers and aligning with governance and security standards. The role emphasizes hands-on development, collaboration with security/compliance, and leadership in deploying scalable AI models and retrieval pipelines using cloud-based