Research Scientist / Engineer – Agents
Description For Research Scientist / Engineer – Agents
ChipStack is revolutionizing the chip design industry by introducing innovative AI-driven solutions to address the increasing complexity of modern semiconductor design. As a Research Scientist/Engineer focused on Agents, you'll be at the forefront of developing intelligent systems that transform how chips are designed.
The role combines cutting-edge research in LLM agent systems with practical implementation in production environments. You'll be working on sophisticated AI agents that can plan, execute, and learn within chip design workflows. This position offers a unique opportunity to bridge theoretical ML research with real-world applications in the semiconductor industry.
The company, backed by prestigious investors including Khosla Ventures, Cerberus, and Clear Ventures, has already established partnerships with over 10 innovative customers, ranging from Fortune 100 companies to cutting-edge AI silicon startups. Their team comprises technical experts from industry leaders like Qualcomm, Nvidia, Google, Meta, and the Allen Institute for AI.
This is an ideal role for someone passionate about both research and practical implementation of AI systems, particularly in the context of agent-based architectures. You'll have the opportunity to influence both research direction and production deployment of agent systems, working directly with chip designers and ML infrastructure engineers to create autonomous workflows for chip design.
The position offers a unique blend of research freedom and practical impact, allowing you to work on challenging problems while seeing your solutions deployed in real-world applications. The company culture emphasizes innovation, collaboration, and high-quality execution, making it perfect for someone who wants to make a significant impact in both AI and semiconductor industries.
Responsibilities For Research Scientist / Engineer – Agents
- Design, engineer, and research agentic systems—software that plans, executes, uses tools, and learns
- Architect and iterate on agentic components: memory, context engineering, tool usage, multi-agent coordination
- Experiment with prompting, finetuning, and orchestration to improve agent performance
- Build scalable infrastructure for prompt iteration/testing, benchmarking, logging, and evaluation
- Assist with pipelines for fine-tuning, automated evaluation, and model deployment
- Work directly with chip designers and ML infra engineers to embed agentic workflows
- Partner with product teams to solve core agent challenges
- Define and evaluate performance metrics for agent systems
- Design goal-oriented agentic workflows to enhance task completion
Requirements For Research Scientist / Engineer – Agents
- 5+ years of combined ML research and/or software engineering experience
- Hands-on experience with LLMs: prompting, finetuning, evaluation
- Strong programming skills
- Solid foundations in distributed systems, data pipelines
- Cloud + on-premise infra experience involving GPUs, Familiarity with Docker
- Excellent communication & a bias toward collaborative problem-solving
- PhD or MS in ML, CS, or related field, or equivalent research + implementation experience
- Ability to build, evaluate, and iterate LLM-based applications
