AI Research Architect for Autonomous Scientific Discovery

atlantic.vc; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

Atlantic portfolio venture seeks researchers and engineers to build an AI-driven platform for scientific discovery. The role focuses on multi-agent systems, knowledge graphs, and autonomous experimentation to enable rapid validation of hypotheses.

You will collaborate directly with founders to design scalable, memory-enabled research workflows, integrate LLMs and open-source models, and deploy robust data pipelines in a cloud environment.

Qualifications

• Experience building agent systems with orchestration and memory.
• Background in AI research workflows and knowledge representation.
• Production-quality Python software development and API design.

Responsibilities

• Design multi-agent research systems and orchestration.
• Build long-term memory architectures for scientific reasoning.
• Create paper ingestion and knowledge extraction pipelines.
• Develop scientific reasoning workflows and connect AI agents to simulations.
• Build autonomous experiment and evaluation loops.
• Design retrieval, planning and orchestration systems.
• Integrate state-of-the-art LLMs and open-source models.
• Develop scalable infrastructure for continuous learning.
• Explore next-generation AI architectures for scientific discovery.

Skills

Multi-agent systems

Agent orchestration

Planning systems

Long-term memory

Knowledge graphs

Autonomous research workflows

RAG architectures

Evaluation frameworks

Python programming

API design

Cloud infrastructure

Docker

Databases

Tools

Docker

REST APIs

Job description

Atlantic portfolio venture seeks researchers and engineers to build an AI-driven platform for scientific discovery. The role focuses on multi-agent systems, knowledge graphs, and autonomous experimentation to enable rapid validation of hypotheses.

You will collaborate directly with founders to design scalable, memory-enabled research workflows, integrate LLMs and open-source models, and deploy robust data pipelines in a cloud environment.