Senior AI Engineer - Solventum

Job Description:

Senior AI Engineer, Enterprise Agentic Solutions

3M Health Care is now Solventum

At Solventum , we enable better, smarter, safer healthcare to improve lives. As a new company with a long legacy of creating breakthrough solutions for our customers’ toughest challenges, we pioneer game-changing innovations at the intersection of health, material and data science that change patients' lives for the better while enabling healthcare professionals to perform at their best. Because people, and their wellbeing, are at the heart of every scientific advancement we pursue.

We partner closely with the brightest minds in healthcare to ensure that every solution we create melds the latest technology with compassion and empathy. Because at Solventum , we never stop solving you.

The ImpactYou’llMake in this Role

As a Senior AI Engineer, Enterprise Agentic Solution , you will serve as the premier technical authority driving the enterprise-wide architecture, engineering, and deployment of Agentic AI and Generative AI platforms. Operating at a highly senior level, your focus extends beyond data science and model training into the rigorous engineering of scalable, high-performance AI systems. You will architect robust, multi-agent frameworks that integrate seamlessly into mission-critical healthcare operations. Furthermore, you will act as a primary technical liaison, partnering directly with executive stakeholders and healthcare customers to translate complex business challenges intohighly reliable, autonomous AI solutions.

Key Responsibilities

Agent Development & Engineering: Build, test, and deploy autonomous, multi-agent systems using frameworks such asAutoGenandLangGraph. Implement the core logic for agent orchestration, toolutilization, and state management.

Advanced RAG & Data Integration: Engineer robust data ingestion pipelines capable of processing complex, multi-modal healthcare data. Implement advanced retrieval techniques, including Graph RAG, and develop solutions for high-accuracy document intelligence (e.g., page-by-page parsing of complex PDFs).

Performance Optimization & Evaluation: Design and execute prompt engineering strategies. Establish andmonitorrigorousevaluation ofmetrics for LLM performance to ensure clinical safety, minimize hallucinations, andoptimizeinference latency in production environments.

Technical Execution & Collaboration: Partner with data scientists, product managers, and cloud engineers to transition AI models into high-concurrency production environments. Establish code quality standards, write comprehensive technical documentation, and mentor junior developers.

Operational Rigor: Build and maintainMLOpspipelines, ensuring secure containerization, CI/CD integration, and comprehensive system telemetry in adherence to healthcare privacy regulations (HIP