Software Engineer (LLM Engineering)

Requirements

• Strong coding skills in Python with a focus on production-grade, maintainable systems.
• Ability to architect and maintain infrastructure as code for complex systems across security, UX, and scalability in the cloud.
• Deep understanding of how language models are trained, how they work internally, and their inherent limitations.
• Experience with the LLM serving stack, such as v LLM, for open-weight models.
• Experience evaluating probabilistic ML systems and managing model tool use, contexts, and loops.
• A hype-detached approach to solving problems and selecting the right technology stack.
• Excellent stakeholder management and the ability to explain technical risks to non-experts.
• Prior success building and scaling systems centered around large language models.
• Experience setting up the underlying hardware or orchestration for ML systems.
• Prior experience building and deploying systems on Google Cloud Platform (GCP).
• Interest or experience in biology, chemistry, or drug discovery, with an interest in applying AI to scientific discovery.
• Familiarity with the latest agentic tooling and developer frameworks.

Responsibilities

• Architect LLM-integrated systems with scalability, security, and user experience considerations from the earliest stages of development.
• Enable telemetry, observability, governance, and cost management.
• Build platform components and tools for routing and making optimal use of various models.
• Implement advanced context management, tool use, skill tooling, and retrieval-augmented generation to enhance research workflows and scale our agentic infrastructure.
• Build rigorous testing for probabilistic systems to ensure model reliability and safety.
• Build and maintain evaluation frameworks for different tasks.
• Develop internal frameworks and IDE integrations to leverage agentic coding and agentic workflows at scale.
• Contribute to shaping best practices and providing a great user experience.
• Support fine-tuning and reinforcement learning efforts in collaboration with AI researchers to optimise models for complex biological and chemical data.
• Partner with researchers to translate scientific needs into technical AI specifications.
• Partner with other parts of the business to unlock LLM-based use cases.

Technologies

• AI
• Architect
• Cloud
• Fine-tuning
• GCP
• Hardware
• Support
• LLM
• Machine Learning
• Python
• Security
• v LLM
• UX UI Design
• LESS
• MCP
• RAG

More

We are Isomorphic Labs, launched in 2021 to advance human health by building on and beyond the Nobel-winning Alpha Fold system.

Our interdisciplinary team of drug discovery experts and machine learning specialists is building powerful predictive and generative AI models to accelerate scientific discovery at digital speed.

We are creating a world-leading drug design engine across multiple therapeutic areas and drug modalities, with an ambition to help solve all disease through AI.

This role sits within our newly formed LLM Engineering team, where we are putting LLMs at the heart of our scientific and business processes.

We offer an inspiring, collaborative, and values-driven culture grounded in being thoughtful, brave, determined, and together.

We work in a hybrid model and expect people to be in the office three days a week, currently Tuesday, Wednesday, and one other day depending on the team.

We are committed to equal employment opportunities and supporting employees with additional needs.

#J-18808-Ljbffr