AI Architect for Software Development

Lattice Semiconductor
San Jose, CA, United States
5 days ago
Apply on www.adzuna.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Compensation
$260,000.0 - $280,000.0
Working hours
Regular working hours
Job source

Tech stack

Artificial Intelligence Program Optimization Field-Programmable Gate Array (FPGA) JSON Python (Programming Language) Software Engineering Tokenization Extensible Markup Language (XML) Data Logging Data Ingestion Pytorch Large Language Models
+5 more
Multi-Agent Systems Prompt Engineering Caching HuggingFace Virtual Agents

Job description

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, * 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.

Requirements

  • 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-but not mandatory.

Benefits & conditions

The base pay for this role is between $260,000 to $280,000 per year. In addition to base salary, we offer an incentive plan bonus, and new hire equity for a competitive total compensation package.

Lattice recognizes that employees are its greatest asset and the driving force behind success in a highly competitive, global industry. Lattice continually strives to provide a comprehensive compensation and benefits program to attract, retain, motivate, reward and celebrate the highest caliber employees in the industry.

Lattice is an international, service-driven developer of innovative low cost, low power programmable design solutions. Our global workforce, some 800 strong, shares a total commitment to customer success and an unbending will to win. For more information about how our FPGA, CPLD and programmable power management devices help our customers unlock their innovation, visit www.latticesemi.com. You can also follow us via Twitter, Facebook, or RSS. At Lattice, we value the diversity of individuals, ideas, perspectives, insights and values, and what they bring to the workplace. Applications are welcome from all qualified candidates.

Lattice Feel the energy.

Pay & Benefits

Consistent with Lattice Semiconductor values and applicable law, we provide the following information to promote pay transparency and equity. We have a market-based pay structure which varies by location. Please note that the base pay range is a guideline, and our compensation range reflects the cost of labor in the U.S. geographic market based on the location of the role. Pay within these ranges varies and depends on job-related knowledge, skills, and relevant work experience.

For candidates who receive and offer, the starting salary will vary based on various factors including, but not limited to, such qualifications as, skill level, competencies, and work location. The range provided may represent a candidate range and may not reflect the full range for an individual tenured employee.

Base Pay Range 273000

In addition to base pay, this role may be eligible for variable/ incentive compensation and/ or equity. In addition, this role is eligible for a comprehensive, competitive benefits package which may include healthcare and retirement plans, paid time off, and more!

About the company

There is energy here…energy you can feel crackling at any of our international locations. It’s an energy generated by enthusiasm for our work, for our teams, for our results, and for our customers. Lattice is a worldwide community of engineers, designers, and manufacturing operations specialists in partnership with world-class sales, marketing, and support teams, who are developing programmable logic solutions that are changing the industry. Our focus is on R&D, product innovation, and customer service, and to that focus, we bring total commitment and a keenly sharp competitive personality.

Energy feeds on energy. If you flourish in a fast paced, results-oriented environment, if you want to achieve individual success within a “team first” organization, and if you believe you can contribute and succeed in a demanding yet collegial atmosphere, then Lattice may well be just what you’re looking for., This position requires a successful background and reference checks and satisfactory proof of your right to work in the United States.

Lattice recognizes that employees are its greatest asset and the driving force behind success in a highly competitive, global industry. Lattice continually strives to provide a comprehensive compensation and benefits program to attract, retain, motivate, reward and celebrate the highest caliber employees in the industry.

Lattice is an international, service-driven developer of innovative low cost, low power programmable design solutions. Our global workforce, some 1,000 strong, shares a total commitment to customer success and an unbending will to win. For more information about how our FPGA, CPLD and programmable power management devices help our customers unlock their innovation, visit www.latticesemi.com. You can also follow us via Twitter, Facebook, or RSS. At Lattice, we value the diversity of individuals, ideas, perspectives, insights and values, and what they bring to the workplace. Applications are welcome from all qualified candidates.

As an E-Verify employer, we use this system to confirm the employment eligibility of all new hires in accordance with federal law. All applicants will be required to complete a Form I-9, Employment Eligibility Verification, upon hire. We do not use E-Verify to pre-screen job candidates and will comply with all E-Verify regulations.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.adzuna.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

3:47 min

Exploring JSON, CBOR, and JOSE for data serialization

Aaron Russell · LIVE

3:15 min

Reversing the caching model for artifact delivery

Thijs Feryn Thijs Feryn · World Congress 2026 Europe

2:35 min

Preventing remote code execution in PyTorch models

Balázs Kiss · World Congress 2023

4:04 min

Defining agentic AI and the tool execution architecture

Rijk van Zanten Rijk van Zanten · Europe 2026 Virtual

2:03 min

Distinguishing type definition constructs from data validation routines

Clemens Vasters Clemens Vasters · World Congress 2025

4:02 min

Core architecture and reasoning loops of AI agents

Benjamin Smith Benjamin Smith · World Congress 2026 Europe

Videos

See all

Related articles

See all