> Markdown version of [/jobs/ext/2709390-agentic-ai-multi-agent-systems-engineer](https://www.wearedevelopers.com/jobs/ext/2709390-agentic-ai-multi-agent-systems-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Agentic AI / Multi-Agent Systems Engineer

- **Company:** UST Inc
- **Location:** Hillsboro, OR, United States (Remote available)
- **Experience:** Expert
- **Salary:** $72,000.0 - $108,000.0
- **Contract:** Temporary contract
- **Skills:** Artificial Intelligence, BIOS, C++ (Programming Language), Code Generation, Nvidia CUDA, Computer Programming, Computer Engineering, Extract Transform Load (ETL), Software Debugging, Linux, Device Drivers, Middleware, GNU Debuggers, Python (Programming Language), Linux Kernel, Unix Shell, OpenCL, PCI Express, Tokenization, Graphics Processing Unit (GPU), GitHub Copilot, Large Language Models, Multi-Agent Systems, Model Validation, Perf (Linux), Linux Development, Kubernetes, Low Latency, ONNX (Open Neural Network Exchange) Format, Slurm, Virtual Agents, Docker
- **Published:** September 4, 2026
- **Apply:** https://www.careerjet.com/job/usa93ee16044df6f7de3b644836219872d/eaa

## About the Role

· Bachelor's degree in Electrical Engineering or Computer Engineering
· 2-4 years of platform debug experience with BIOS/FW/platform ingredients
· Required Experience & Knowledge
· Linux & Systems
· Strong Linux development and debugging skills
· Understanding of processes, threads, memory, PCIe, DMA, kernel modules, and device drivers
· Ability to debug workloads across the application * runtime * driver stack
· Agentic AI & Multi-Agent Systems
· Hands-on development of multi-agent workloads
· Experience with agent orchestration, tool/function calling, memory planning and agent-to-agent communication
· Experience with agent frameworks such as LangGraph/LangChain, AutoGen, or CrewAI
· Models & Inference
· Strong understanding of LLMs, SLMs and multimodal models
· Knowledge of Transformer architecture, attention, tokenization, context windows, and KV cache
· Hands-on experience with model selection, evaluation, and deployment
· Understanding of model formats and optimization: ONNX, Open VINO IR, safe tensors, quantization (FP16/BF16/INT8/INT4)
· Experience with inference engines: Open VINO, ONNX Runtime, vLLM, llama.cpp, or TGI
· Understanding of prefill vs. decode, batching, continuous batching, speculative decoding, and KV-cache management
· Ability to optimize for latency, throughput, tokens/sec, memory footprint, and accelerator utilization
· Accelerator & Compute Stack
· Understanding of the complete execution path: Agent * Model * Inference Engine * Middleware * Compute Runtime * GPU Driver * Hardware
· Understanding of GPU memory, kernel execution, synchronization, device selection and host/device data movement
· Familiarity with middleware/accelerator compute runtimes: OMZ/OneAPI/SYCL, Level Zero, or OpenCL
· Programming & Development
· Strong Python skills
· Working knowledge of C/C++
· Git/GitHub and Linux shell proficiency
· Debugging tools expertise
· Practical use of GitHub Copilot for development, debugging and code generation
· Docker/container fundamentals
· Performance Engineering
· Ability to benchmark and profile AI workloads
· Understanding of latency, throughput, tokens/sec, GPU utilization, memory bandwidth and CPU/GPU bottlenecks
· Ability to identify performance issues at different stack levels
· Desired Skills
· Intel GPU architecture and Linux GPU driver stack
· DRM/i915 and newer Intel GPU driver architecture
· Intel GPU profiling and telemetry
· Speculative decoding and continuous batching experience
· Tensor/pipeline parallelism knowledge
· Model conversion, graph optimization and operator/kernel fusion
· MCP (Model Context Protocol)
· Advanced RAG architectures
· Agent observability/tracing
· Model routing and dynamic model selection
· Distributed/multi-agent execution
· CUDA/HIP/ROCm familiarity
· Kubernetes, Ray or Slurm experience
· Distributed inference knowledge
· Linux kernel/GPU debugging
· perf, gdb, tracing and GPU profiling tools
Compensation can differ depending on factors including but not limited to the specific office location, role, skill set, education, and level of experience. UST provides a reasonable range of compensation for roles that may be hired in various U.S. markets as set forth below.
Role Location: Oregon, Agentic AI, Linux Kernel, OpenVINO, LangChain, RAG, Kubernetes

## Description

UST is searching for an Agentic AI / Multi-Agent Systems Engineer who will develop and optimize multi-agent AI systems and agentic workloads.
The opportunity:
· Work with agent frameworks and orchestration technologies to design scalable solutions
· Select, evaluate, and deploy appropriate models and inference engines based on workload requirements
· Debug and optimize performance across the full stack: agent * model * inference engine * hardware
· Benchmark and profile AI workloads to identify and resolve performance bottlenecks
· Optimize model execution for latency, throughput, memory efficiency and accelerator utilization
· Collaborate on the complete execution path from agent logic through GPU hardware
This position description identifies the responsibilities and tasks typically associated with the performance of the position. Other relevant essential functions may be required.


## Related Videos

- [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure)
- [10M Data Records Lost, Underwater Computing, and Psychedelic Fish - Matthias Geniar](https://www.wearedevelopers.com/videos/1908-10m-data-records-lost-underwater-computing-and-psychedelic-fish-matthias-geniar)
- [Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬](https://www.wearedevelopers.com/videos/100355-running-secure-life-science-research-at-scale-using-hybrid-gpu-hpc-and-kubernetes)
- [Docker network without Docker](https://www.wearedevelopers.com/videos/1418-docker-network-without-docker)
- [How to Submit CFPs and Get into Public Speaking - Moran Weber](https://www.wearedevelopers.com/videos/2112-how-to-submit-cfps-and-get-into-public-speaking-moran-weber)
- [Docker exec without Docker](https://www.wearedevelopers.com/videos/1094-docker-exec-without-docker)

## Related Articles

- [A 5-Step Open-Source Setup for Agentic Engineering](https://www.wearedevelopers.com/magazine/738-a-5-step-open-source-setup-for-agentic-engineering)
- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [Highest Paying Tech Companies for Developers](https://www.wearedevelopers.com/magazine/220-highest-paying-tech-companies-for-developers)
- [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path)
- [The Overflow: AI and Agentic Coding](https://www.wearedevelopers.com/magazine/721-the-overflow-ai-and-agentic-coding)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)