Job Details:

Job Description:

Role Overview

We are seeking a highly experienced AI Technical Leader to drive the design and deployment of next-generation agentic AI systems optimized for FPGA/ASIC platforms.

This role sits at the convergence of:

• Large Language Models (LLMs)

• Agentic AI & autonomous systems

• Retrieval-Augmented Generation (RAG)

• Hardware-aware AI system design (FPGA / ASIC / EDA)

You will define system architecture, lead technical strategy, and deliver scalable AI solutions that tightly integrate software intelligence with hardware acceleration, with a strong focus on AI model optimization and deployment on FPGA.

Key Responsibilities

AI Architecture & System Design

• Architect and implement end-to-end agentic AI systems (data → reasoning → action)

• Design scalable multi-agent orchestration frameworks

• Build enterprise-grade RAG pipelines for knowledge integration and retrieval

• Define system-level architecture bridging cloud, edge, and hardware acceleration

Agentic AI & LLM Development

• Develop advanced agent workflows, including:

  • Tool-using agents
  • Planning and reasoning agents
  • Multi-agent collaboration systems

• Evaluate and integrate state-of-the-art LLMs (open-source and proprietary)

• Optimize prompting, memory, and reasoning strategies for performance and reliability

AI Model Optimization on FPGA (Core Focus)

• Lead AI model optimization and deployment on FPGA platforms, including:

  • Quantization (INT8 / BF16 / mixed precision)
  • Graph compilation and operator fusion
  • Model partitioning across CPU/GPU/FPGA
  • Memory and bandwidth optimization

• Develop workflows to map AI models (e.g., CV, LLM inference) from PyTorch/Hugging Face to FPGA

• Enable low-latency, high-efficiency inference pipelines on FPGA-based systems

• Collaborate with hardware teams to align model architecture with FPGA constraints (DSP, BRAM, interconnect)

Hardware-Aware AI Co-Design

• Co-design AI systems with:

  • FPGA acceleration
  • ASIC platforms
  • Heterogeneous compute architectures (CPU/GPU/FPGA)

• Integrate AI workflows into EDA toolchains and hardware design flows

• Drive innovations in software-hardware co-optimization

Framework & Platform Development

• Build internal AI platforms leveraging:

  • LangChain
  • LlamaIndex
  • Custom agent orchestration frameworks​

• Develop reusable components for:

  • Memory management
  • Tool integration
  • Knowledge retrieval and indexing​

• Enable scalable deployment pipelines for AI applications on FPGA

Technical Leadership

• Lead architecture design reviews and set technical direction

• Mentor senior engineers and guide cross-functional teams

• Drive innovation at the intersection of AI systems and semiconductor platforms

What Makes This Role Unique

• Define agentic AI architecture for hardware-native AI systems

• Work at the frontier of:

  • AI reasoning systems

  • FPGA-based acceleration

  • Next-generation computing platforms

​

• High-impact role shaping AI + semiconductor convergence

Impact

You will enable a new class of intelligent systems where AI agents are tightly coupled with hardware, delivering:

• Real-time decision-making pipelines

• Efficient, scalable AI deployment on FPGA

• End-to-end automation from model to hardware execution

Summary

This role is ideal for a senior technical leader who can:

• Bridge LLM + Agentic AI + RAG with FPGA/ASIC system architecture

• Drive AI model optimization and deployment on FPGA

• Lead innovation in next-generation AI + hardware integrated systems

Qualifications:

Required

• Strong experience in LLMs, agentic AI, or RAG systems

• Proven track record in large-scale AI system architecture and deployment

• Solid programming skills in Python/C++ and modern AI frameworks

• Experience designing distributed or production AI systems

• Strong system-level thinking across software and infrastructure

Preferred / Plus

• Experience with FPGA, ASIC, or hardware acceleration platforms

• Familiarity with FPGA development flows and toolchains (e.g., synthesis, compilation, HLS, runtime)

• Experience with AI model optimization for hardware (quantization, compilation, deployment)

• Exposure to EDA tools and semiconductor design workflows

• Background in heterogeneous computing systems (CPU/GPU/FPGA)

Job Type:

Regular

Shift:

Shift 1 (China)

Primary Location:

Shanghai, China

Additional Locations:

Posting Statement:

All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance.