Senior AI Software Engineer

ChenMed

1d•Onsite

About The Position

This AI development team role at ChenMed is focused on building AI Agent and Autonomous solutions that enhance our care delivery model. We operate like an internal startup — driven by our mission to transform senior care and deliver more good days for our patients. You'll work alongside seasoned ChenMed team members and fresh talent, bringing disruptive thinking to a collaborative, high-growth environment where zero-to-one ideas become production reality. We're looking for a Full Stack AI Software Engineer who thrives in ambiguity, works autonomously, and executes with purpose and speed.

Requirements

Superb knowledge of Atlassian suite (Bitbucket/Jira/Confluence) or similar tools; expert-level proficiency in Microsoft Office Suite.
Expert in at least 2 technical domains with strong ability to anticipate and resolve software issues.
Self-directed with ability to lead individuals or small teams, work with minimal supervision, and exercise independent judgment.
Skilled at breaking multi-week objectives into defined tasks and managing projects to deadlines without unnecessary time pressure.
Cross-functional influencer who builds consensus, drives best practices, and communicates core controls to business units.
Proactively develops programs that improve productivity, revenue, and customer value.
Effective mentor who coaches junior team members, fosters a positive learning environment, and sets measurable objectives.
Strong written and verbal English communication skills.
Bachelor degree in Computer Science, Computer Information Systems, Software Engineering, Software Development, Mathematics or a related field OR additional experience above the minimum will be considered in lieu of the required education on a year-for-year basis required
A minimum of 5 years’ work experience as a software engineer or similar IT role or related field required

Nice To Haves

IT certification in Java, C, Objective-C, C++, Perl & Python or similar formats preferred

Responsibilities

Proven experience in building and deploying AI application backends using FastAPI (Python) or Node.js/Express (TypeScript), containerization with Docker, and cloud deployment on platforms such as AWS, Azure, or GCP.
Experience implementing Retrieval-Augmented Generation (RAG) pipelines using vector stores such as Pinecone, Chroma, or pgvector, including embedding generation, document chunking strategies, and semantic search optimization.
Ability to integrate and manage large language model APIs (OpenAI, Anthropic, etc.), configure model parameters, handle token management, and design multi-step reasoning pipelines using LangGraph or similar orchestration frameworks.
Develops and ships software in an Agile/Scrum environment, taking full ownership from inception through launch and support.
Manages projects within a specialized area, coordinating with leadership on schedules, goals, design criteria, and methodology.
Communicates clearly with stakeholders to align on requirements, expectations, and timelines; escalates proactively when deadlines are at risk.
Exercises independent judgment with manager feedback, following defined processes, methods, and procedures.
Guides solution delivery end-to-end, providing appropriate documentation and sharing knowledge, lessons learned, and best practices with the team.
Performs other duties as assigned and modified at manager's discretion.