One Health Link · 21 hours ago

Senior AI Engineer

United States

Full-time

Remote

Senior Level

Maximize your interview chances

AnalyticsElectronic Health Record (EHR)

Hiring Manager

Yi Zheng

Insider Connection @One Health Link

Discover valuable connections within the company who might provide insights and potential referrals.
Get 3x more responses when you reach out via email instead of LinkedIn.

Responsibilities

Design, develop and deploy purposed built AI agents for our healthcare application. Work along the side with other experienced Python/AI engineers, building the One Health Link next generation AI Agent platform

Design and optimize RAG pipelines for enhanced information retrieval and response generation.

Implement and evaluate agentic solutions that automate and enhance user interactions.

Play the role of tech lead for the entire RAG/LLM part of the tech team

Create the next generation platform design that will adopt agentic patterns

Collaborate with DevOps when creating and maintaining CI/CD pipelines,

Mentor other engineers in the ways of RAG, and agentic patterns, take the team from prompt engineering to building multi task, adaptive agents

Collaborate with cross-functional teams to define AI product requirements, project specifications, and system architectures.

Preprocess and analyze large datasets to extract meaningful insights that drive model training and optimization.

Conduct thorough evaluations and experiments to validate and iterate on model performance, ensuring reliability and scalability.

Integrate closed and open-source AI models seamlessly into production environments.

Maintain, monitor, and improve the performance of existing AI systems, ensuring their scalability and alignment with organizational objectives.

Document processes, methodologies, and findings, clearly communicating complex technical concepts to non-technical stakeholders through reports and presentations.

Stay current with the latest advancements in generative AI, LLM development, and related technologies to continually enhance product capabilities.

Qualification

Find out how your skills align with this job's requirements. If anything seems off, you can easily click on the tags to select or unselect skills to reflect your actual expertise.

PythonML/AI modelsDistributed systemsLangChainLlamaIndexTensorFlowPyTorchHugging FaceKerasLarge language modelsRetrieval-augmented generationAgentic frameworkEvaluation frameworksAPIsNoSQL databasesRelational databasesTesting distributed systemsFine tuning LLMsHealthcare systemsMLOps practicesDeepEvalRagasPromptFooCaching systemsEvent-driven architecturesMulti-tier architecturesEthical considerations in AI

Required

Fluent in Python (can build and deploy web APIs/Services, CLIs, libraries, and scripts). Experience with frameworks like LangChain, LlamaIndex, TensorFlow, PyTorch, Hugging Face, Keras etc.

Proven experience in developing and deploying production-grade applications and services using ML/AI models, including large language models (LLMs), retrieval-augmented generation (RAG) systems, evals, agentic framework.

Hands on experience building AI systems with LLM models, open source or commercial LLM variants

Hands on experience and proficiency in building production grade RAG systems, using LlamaIndex, LangChain, etc

Hands on experience applying agentic patterns to build real world copilot/assistant-type agents

Hands on experience with evaluation frameworks like DeepEval, Ragas, PromptFoo, etc

Proven track record in architecting and building distributed systems

Strong knowledge of designing, analyzing, and troubleshooting APIs services, NoSQL and relational databases, caching systems, event-driven and multi-tier architectures

Strong knowledge on how to write tests for distributed systems effectively

Comfortable working in a fast-paced environment with a strong ability to adapt to changing priorities

Strong written and verbal English communication skills