Agentic AI Systems Development
Design and implement agent-based systems that support complex scientific workflows.
Develop capabilities including
Tool calling and tool orchestration
Multi-step reasoning workflows
Retrieval-augmented generation (RAG)
Knowledge-grounded AI systems
Human-in-the-loop decision workflows
Multi-agent collaboration patterns
Build reusable components for
Agent orchestration
Context management
Memory and state handling
Workflow planning and execution
Scientific tool integration
Evaluate emerging agent frameworks and contribute to standards and best practices across projects.
Scientific AI & Model Integration
Integrate foundation models and scientific AI models into end-to-end workflows.
Examples may include
Protein language models
Structure prediction models
Biological foundation models
Knowledge graph-based systems
Predictive machine learning models
Develop reusable APIs, services, and interfaces that allow AI agents and applications to consume scientific models and computational tools.
Collaborate with scientific domain experts to identify appropriate modeling approaches and evaluate solution effectiveness.
Knowledge Systems & Retrieval
Design and implement knowledge-driven AI systems that connect LLMs and agents with enterprise and scientific data.
Develop solutions utilizing
Retrieval-augmented generation (RAG)
Vector databases
Knowledge graphs
Graph-RAG architectures
Scientific literature and domain knowledge repositories
Ensure AI systems leverage authoritative knowledge sources and support traceability and explainability.
AI Workflow Engineering
Develop end-to-end workflows that combine
Data ingestion and preparation
Knowledge retrieval
Model inference
Agent orchestration
Scientific analysis
Create reusable workflow patterns that can be applied across multiple scientific domains and projects.
Contribute to architectural decisions regarding workflow design, model integration, and AI system composition.
Evaluation & Responsible AI
Develop evaluation frameworks for AI systems, agents, and workflows.
Establish approaches for measuring
Accuracy
Reliability
Scientific relevance
Hallucination rates
Workflow effectiveness
User adoption and impact
Support responsible AI practices including transparency, traceability, and governance requirements.
Collaboration & Scientific Partnership
Partner closely with
AI domain leads
Scientists and researchers
Data engineering teams
Platform engineering teams
Enterprise AI platform teams
Translate scientific requirements into technical solutions and provide guidance on AI capabilities, limitations, and implementation approaches.
Contribute to technical design reviews and mentor junior team members where appropriate.
Core Competencies
Strong engineering background in AI and machine learning systems.
Hands-on experience with
Large Language Models (LLMs)
Agent frameworks (LangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, or similar)
Retrieval-Augmented Generation (RAG)
Vector databases
API-driven architectures
Python-based AI and ML ecosystems
Understanding of
Machine learning lifecycle and evaluation
Scientific computing workflows
Distributed systems and scalable architectures
Knowledge graph concepts and graph-based AI approaches
Ability to operate effectively in highly collaborative, cross-functional scientific environments.
Core Success Measures
Delivery of reusable AI capabilities and agentic workflows
Adoption of AI solutions by scientific teams
Quality and reliability of deployed AI systems
Reduction of manual effort through workflow automation
Reusability of components across multiple scientific domains
Effective collaboration with scientific and engineering stakeholders
Key Relationships
Works closely with
GCF6 Scientific AI Leads
Scientists and domain experts
Data Engineering teams
Enterprise AI Platform teams
Infrastructure and production engineering organizations
Decision Authority
Makes implementation decisions regarding
Agent architectures
Workflow composition
Knowledge retrieval strategies
Model integration approaches
Evaluation methodologies
Influences broader architectural direction through technical expertise and collaboration with senior technical leaders.
Qualifications
Basic Qualifications
BS or MS in Computer Science, Engineering, Computational Biology, Bioinformatics, or related field
Strong hands-on experience developing AI and machine learning solutions
Expertise in Python and modern AI/ML development frameworks
Experience designing and implementing production-quality software systems
Preferred Qualifications
Experience with LLMs, agentic AI systems, and workflow orchestration
Experience with RAG, vector databases, and knowledge-driven AI architectures
Experience integrating scientific or domain-specific AI models
Familiarity with biological, biomedical, or life sciences data
Experience with cloud AI platforms (AWS Bedrock, SageMaker, Azure AI, or equivalent)
Familiarity with knowledge graphs, Graph-RAG, or scientific knowledge systems
Experience working closely with researchers and domain experts.
Preferred Experience
Bachelor's with 5–9 years of experience.
EQUAL OPPORTUNITY STATEMENT
Amgen is an Equal Opportunity employer and will consider you without regard to your race, color, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, or disability status.
We will ensure that individuals with disabilities are provided with reasonable accommodation to participate in the job application or interview process, to perform essential job functions, and to receive other benefits and privileges of employment. Please contact us to request accommodation.
.
