AI Architect for Software Development

Lattice Semiconductor Corp; United States; On-site; USD 260,000 - 280,000; Full time

Benefits offered by this job

Healthcare benefits

Retirement plans

Paid time off

Equity options

Job summary

Lattice Semiconductor Corp is seeking an AI Architect to lead the design and development of large-scale Agentic AI systems that automate complex workflows using LLMs. The ideal candidate will excel in multi-agent systems architecture and model optimization.

The role requires strong experience in ML products, with key responsibilities including designing workflows, implementing LLM calls, and ensuring AI safety. Competitive compensation including benefits and equity is offered for this position.

Qualifications

• 5+ years building ML or LLM-powered products.
• Experience with LLM fine-tuning and prompt engineering.
• Strong understanding of LLM internal architecture.

Responsibilities

• Design multi-agent workflows and orchestrate specialized agents.
• Implement schema-bound LLM calls and evaluate models.
• Develop multi-layer guardrails and logging pipelines.

Skills

ML or LLM-powered product development

Prompt engineering

Python

PyTorch

Building robust RAG pipelines

Tools

HuggingFace

vLLM

LangChain

Job description

AI Architect

We are looking for an AI Architect to design and lead the development of a large‑scale Agentic AI system that automates complex engineering workflows using LLMs, VLMs, and structured reasoning. You will architect multi‑agent workflows, build high‑quality training datasets, fine‑tune and optimize frontier models, and design the guardrails, retrieval pipelines, and evaluation frameworks required to run AI safely and reliably in production. This role is ideal for someone who excels in AI systems architecture, agent design, LLM/RAG pipelines, and model optimization.

Key Responsibilities

• Design multi‑agent workflows with an orchestrator, specialized agents, and shared memory.
• Define agent interfaces, policies, and error‑handling/repair strategies.
• Implement strict schema‑bound LLM calls (JSON, XML, structured tool commands).
• Select, distill, fine‑tune, and evaluate LLM/SLM/VLA models.
• Design prompt templates, adapters, LoRA modules, and controlled‑generation methods.
• Build document ingestion pipelines with chunking, metadata tagging, and embeddings.
• Build domain‑aware RAG systems with citation‑based referencing.
• Develop multi‑layer guardrails using schema validation, rule‑based checks, and policy engines.
• Implement self‑critique, repair loops, and fallback strategies for model outputs.
• Build model serving pipelines (vLLM/TGI/Triton), caching, batching, and streaming.
• Implement logging, tracing, observability, and offline evaluation pipelines.

Required Qualifications

• 5+ years building ML or LLM‑powered products (multi‑agent systems preferred).
• Experience with LLM fine‑tuning (LoRA/QLoRA), distillation, and prompt engineering.
• Strong understanding of LLM internal architecture (transformers, attention, tokenization).
• Expertise in Python, PyTorch, and modern AI frameworks (HuggingFace, vLLM, LangChain).
• Experience building robust RAG pipelines (embedding optimization, retrieval metrics).
• Experience designing structured model interactions (JSON schema, function‑calling, tool‑use).
• Experience with embedded, hardware, or FPGA workflows—though not mandatory.

Benefits and Compensation

The base pay for this role is between $260,000 to $280,000 per year. The role may also be eligible for variable incentive compensation and/or equity, as well as a comprehensive benefits package that may include healthcare and retirement plans, paid time off, and other customary benefits. A competitive total compensation package will be offered.

Additional Information

This position requires successful background and reference checks and satisfactory proof of your right to work in the United States. Applications are welcome from all qualified candidates.