Principal AI Engineer

About InsightRx

InsightRx is pioneering the future of precision medicine. We envision a world in which all medications work as intended, maximally effective and safe. Our platform leverages quantitative pharmacology and artificial intelligence to optimize therapeutic outcomes across the spectrum of drug development and patient care. It has benefited close to 2 million patients across the U.S. and Europe. 

We serve two core verticals:

• Life Sciences: Accelerating drug development with AI-powered PK/PD modeling and decision support. This includes building AI agents that streamline pharmacometric workflows, enabling scientists to run complex analyses, grounded in clinical trial data.
• Healthcare Delivery: Enabling precision dosing and individualized treatment at the point of care. Our focus here includes developing robust retrieval-augmented generation (RAG) pipelines to support clinicians with real-time, context-aware dosing guidance.

AI is central to our next phase of growth. We're building agentic AI systems that enhance how clinical pharmacologists, pharmacists, and translational scientists conduct modeling and make therapeutic decisions.

About the Role

We are looking for a Principal AI Engineer to lead the design and implementation of advanced AI systems—particularly in the areas of agentic AI and production-grade LLM applications. This role blends deep technical expertise with strategic problem-solving to build intelligent systems that are robust, efficient, and impactful.

Key Responsibilities

AI System Architecture & Design

• Architect agentic AI systems that solve complex business problems without unnecessary complexity
• Lead prompt engineering initiatives and develop advanced prompting strategies for production use
• Guide decisions on AI model selection, deployment, and optimization
• Establish best practices for AI system reliability, observability, and performance

Production AI Development

• Build and maintain production-grade LLM applications using modern Python frameworks
• Implement robust queuing systems (e.g., SQS, Redis) for asynchronous workloads
• Design fault-tolerant systems that gracefully handle LLM errors and outages
• Develop testing strategies for non-deterministic AI components

Technical Leadership

• Mentor engineers on AI best practices and architectural patterns
• Collaborate with cross-functional teams to translate business needs into scalable technical solutions
• Drive adoption of modern agentic frameworks and tools across the organization
• Contribute to AI roadmap planning and technical strategy

Qualifications

Technical Expertise

• Prompt Engineering: Advanced experience crafting, optimizing, and productionalizing LLM prompts
• Agentic AI: Deep understanding of agentic design patterns and orchestration strategies
• LLM Operations: Hands-on experience deploying and maintaining LLM-based systems in production
• Modern Python: Expert-level proficiency in Python and its async ecosystem
• AI Frameworks: Experience with tools like LangGraph, PydanticAI, or similar
• Model Knowledge: Familiarity with Claude, GPT-4, and other foundation models
• Distributed Systems: Strong grasp of queuing systems and asynchronous task handling

Experience & Education

• BSc. in Computer Science, Machine Learning, or related field—or equivalent practical experience
• 5+ years of experience building and scaling production AI/ML systems
• Genuine interest in applying AI to clinical and scientific domains

What We're Looking For

Technical Mindset

• Pragmatic approach to AI—knows when to build vs. when to simplify
• Strong debugging and troubleshooting capabilities
• Comfort with evaluating and A/B testing model-driven features

Leadership Qualities

• Ability to mentor and scale an engineering team
• Strong written and verbal communication skills
• Experience leading complex initiatives from ideation to deployment

Cultural Fit

• Intellectual curiosity and willingness to learn domain-specific concepts
• Passion for building AI systems that have real-world healthcare impact
• Thrives in dynamic, fast-evolving technical environments

What You’ll Build

• Scalable agentic AI systems powering the Apollo-AI platform
• Prompt engineering pipelines and LLM performance evaluation tools
• Fault-tolerant AI infrastructure for healthcare and life sciences applications
• Internal frameworks to accelerate cross-team AI adoption

Join InsightRx to shape the future of AI in medicine. You’ll be at the forefront of building intelligent systems that accelerate drug development and improve patient care.