Software Engineer, Agentic AI

About the role

The organization operates in the scientific research software industry, providing a comprehensive digital science platform that integrates best-in-class applications used by over 2 million scientists globally. It addresses the challenge of fragmented scientific data by offering a unified ecosystem that enhances dynamic, multi-dimensional decision-making. The team supports customers in over 180 countries, aiming to accelerate scientific innovation for health, environmental, and safety improvements.

The SOFTWARE ENGINEER, AGENTIC AI role focuses on developing an AI agent central to the organization's Luma platform. This position involves end-to-end ownership of the agent's reasoning, tool integration, memory, failure recovery, and performance validation. The role requires building and maintaining robust, production-quality AI-driven software, advancing the organization's capabilities in autonomous AI tools to enhance scientific research workflows.

Responsibilities

• Develop and maintain the AI agent's control flow, including subagents, long-running tasks, checkpointing, and recovery.
• Engineer context management strategies to maintain agent coherence during extended experiments.
• Design and implement tools interfacing with the agent for instrument orchestration, scheduling, data capture, and developer workflows.
• Implement persistent memory and state management for the agent to leverage past interactions.
• Establish permissions and sandboxing to control agent autonomy and error containment.
• Protect the agent from prompt injection and untrusted inputs, ensuring auditability and compliance.
• Evaluate and debug agent performance on multi-step tasks, improving reliability, accuracy, cost, and latency.
• Adapt architecture as AI models evolve, removing unnecessary scaffolding.
• Lead AI-first development processes, utilizing coding agents while ensuring architecture, correctness, and security.
• Manage infrastructure, configuration, and deployment environments for reliable agent operation.
• Deliver services and interfaces around the agent using Python, Node.js/TypeScript, and React.

Requirements

• Approximately 10 years of software engineering experience.
• Hands-on experience building and deploying LLM-powered agents in production environments.
• Strong background in AI-native engineering, utilizing autonomous coding agents.
• Expertise in context engineering, memory, and retrieval in long-running LLM applications.
• Degree or higher education in Computer Science, Engineering, or related technical field.
• Interest in life sciences, laboratory instrumentation, or automation is preferred.