AI工程师 – GenAI应用开发

Our team members are at the heart of everything we do. At Cencora, we are united in our responsibility to create healthier futures, and every person here is essential to us being able to deliver on that purpose. If you want to make a difference at the center of health, come join our innovative company and help us improve the lives of people and animals everywhere. Apply today!

We are seeking a hands-on AI Engineer to build and ship Generative AI applications — from LLM-powered features and RAG pipelines to production-grade AI agents. This is an engineering-focused role centered on writing high-quality software, building AI apps end-to-end, and deploying them reliably to production. You will work closely with the AI Architect and product stakeholders to turn architectural designs into working, tested, deployed systems.

Build and deploy LLM-powered applications, RAG pipelines, and AI agents using Python.

Implement retrieval-augmented generation systems: chunking, embeddings, vector search, hybrid retrieval, and re-ranking.

Develop AI agents using agentic frameworks (LangChain, LangGraph, CrewAI) under architectural guidance.

Build and maintain REST APIs (FastAPI or Flask) that expose AI functionality to applications and services.

Take AI solutions from proof-of-concept to production: containerize (Docker), deploy, and monitor.

Implement LLM evaluation and testing (Ragas, LangSmith, or custom eval harnesses) to catch regressions and hallucinations.

Apply LLMOps/MLOps practices: CI/CD pipelines, prompt/version management, automated testing, and monitoring of latency, cost, and quality.

Write clean, maintainable, well-tested software following solid engineering fundamentals.

Collaborate with architects, engineers, and product owners to translate designs into working software.

Databricks — Unity Catalog, Delta Lake, Databricks Apps, and Databricks AI Gateway for model routing and governance.

Microsoft Azure, including Azure AI Foundry for model deployment and orchestration.

Multi-LLM provider access — Anthropic Claude, OpenAI (GPT & Codex), and other foundation models.

ployment.

Bachelor's degree in Computer Science, AI/ML, or a related field (or equivalent practical experience).

5+ years of software engineering experience, including 2+ years hands-on with GenAI / LLM-based applications.

Practical experience building RAG pipelines: embeddings, vector databases (Pinecone, Weaviate, FAISS, ChromaDB, pgvector), and prompt engineering.

Experience with at least one agentic / orchestration framework (LangChain, LangGraph, CrewAI, or similar).

Experience building and deploying REST APIs (FastAPI or Flask).

Familiarity with containerization and deployment (Docker; basic Kubernetes a plus).

Working knowledge of at least one cloud platform (Azure, AWS, or GCP) for AI workload deployment.

Comfortable working in fast-paced environments and shipping iteratively.

Experience with LLM evaluation frameworks (Ragas, LangSmith, DeepEval, or custom benchmarks).

Exposure to Kubernetes, CI/CD pipelines, and production monitoring/observability tools.

Experience with SQL / NL-to-SQL pipelines or structured-data integration for AI apps.

Familiarity with MCP (Model Context Protocol) or building tool-calling agents.

Prior experience taking AI features from POC through full production ownership.

We strongly prefer candidates who bring healthcare knowledge alongside their AI/software engineering skills. Our AI applications run on healthcare distribution and specialty pharmacy data — hands-on experience with healthcare distribution data, pharmacy/NDC-level data, or healthcare EMR/EHR systems (HL7, FHIR, claims) is a strong plus.

We provide compensation, benefits, and resources that enable a highly inclusive culture and support our team members’ ability to live with purpose every day. In addition to traditional offerings like medical, dental, and vision care, we also provide a comprehensive suite of benefits that focus on the physical, emotional, financial, and social aspects of wellness. This encompasses support for working families, which may include backup dependent care, adoption assistance, infertility coverage, family building support, behavioral health solutions, paid parental leave, and paid caregiver leave. To encourage your personal growth, we also offer a variety of training programs, professional development resources, and opportunities to participate in mentorship programs, employee resource groups, volunteer activities, and much more. For details, visit

Cencora is committed to providing equal employment opportunity without regard to race, color, religion, sex, sexual orientation, gender identity, genetic information, national origin, age, disability, veteran status or membership in any other class protected by federal, state or local law.

The company’s continued success depends on the full and effective utilization of qualified individuals. Therefore, harassment is prohibited and all matters related to recruiting, training, compensation, benefits, promotions and transfers comply with equal opportunity principles and are non-discriminatory.

Cencora is committed to providing reasonable accommodations to individuals with disabilities during the employment process which are consistent with legal requirements. If you wish to request an accommodation while seeking employment, please call 888.692.2272 or email . We will make accommodation determinations on a request-by-request basis. Messages and emails regarding anything other than accommodations requests will not be returned

- Proficiency in Python for building LLM-powered applications, RAG pipelines, and AI agents.

- Experience implementing retrieval-augmented generation systems, including chunking, embeddings, vector search, hybrid retrieval, and re-ranking.

- Hands-on experience with agentic frameworks such as LangChain, LangGraph, or CrewAI.

- Ability to build and maintain REST APIs using FastAPI or Flask.

- Skills in containerizing applications with Docker and deploying/monitoring AI solutions in production.

- Knowledge of LLM evaluation and testing tools (e.g., Ragas, LangSmith) to detect regressions and hallucinations.

- Familiarity with LLMOps/MLOps practices, including CI/CD pipelines, prompt/version management, automated testing, and monitoring latency, cost, and quality.

- Strong software engineering fundamentals, with a focus on writing clean, maintainable, well-tested code.

- Collaborative skills to work with architects, engineers, and product owners in translating designs into deployed systems.

- Experience with Databricks (Unity Catalog, Delta Lake, Databricks Apps, AI Gateway) and Microsoft Azure is preferred.