C the Signs
Senior AI Developer (Agentic Healthcare Application)
C the Signs, New York, New York, us, 10261
Senior AI Developer (Agentic Healthcare Application)
We are looking for a forward‑thinking Senior AI Developer to architect and build the next generation of autonomous AI applications. You will move beyond standard prompt engineering to design Agentic Workflows—systems where LLMs function as reasoning engines that can plan multi‑step tasks, utilize external tools (APIs, databases), and collaborate with other specialized agents to achieve high‑level goals.
Experience working with the GCP Vertex AI ecosystem is essential. In this role you will design agents capable of complex reasoning and tool usage, leveraging Google's managed infrastructure (Vertex AI Vector Search, Cloud Run, and BigQuery) to ensure reliability, security, and performance.
Key Responsibilities
Architecting and implementing agentic workflows
Design autonomous loops: build stateful control loops (Perception → Reasoning → Action) where agents can interpret clinical data, plan necessary checks, and generate risk assessments
Conversational agentic workflow: chatbot‑style user experience powered by LLM
GCP integration: leverage Vertex AI for model serving and LLM reasoning, optimizing for long‑context windows to process complex medical history
RAG & grounding: implement “Enterprise Grounding” using Vertex AI Vector Search to ensure all agent outputs are strictly cited against official medical literature
Data & tool integration: build robust Python tools (function calling) that allow agents to securely query BigQuery or other datastores for patient demographics and symptoms
Security & compliance: ensure all AI operations comply with HIPAA/GDPR standards, implementing strict PII masking and data governance within Google Cloud
System reliability: deploy agents on Vertex AI, Cloud Run, or GKE, ensuring low‑latency inference and high availability for clinical users
Agent monitoring: implement effective AI agent execution monitoring and alert system to ensure SLA, safety, and security compliance
Leadership & strategy: guide a team of engineers in MLOps best practices (CI/CD for models, evaluation pipelines)
Evaluation: implement “LLM‑as‑a‑Judge” frameworks to automatically test agent accuracy against golden datasets of clinical cases
Required Technical Skills
Core AI: deep proficiency with LangChain or LangGraph, and specific experience with the Vertex AI SDK and ADK (Agent Development Kit)
Conversational workflow: Google Dialogflow CX
LLMs: expertise in prompting and configuring LLMs, specifically utilizing function calling and context caching
Experience integrating LLMs into platform and application workflow, with MCP protocols
RAG/embeddings: expert level experience in design and implementation of RAG‑based systems using embeddings and vector databases
Data engineering: strong SQL skills for BigQuery; experience with vector databases (Pinecone, Milvus, or Vertex Vector Search)
Backend engineering: mastery of Python (FastAPI) and containerization (Docker) for deploying microservices to Cloud Run or GKE
Healthcare domain: familiarity with handling unstructured medical text or clinical guidelines (highly preferred)
Qualifications
Experience:
5+ years of software development experience
2+ years of hands‑on experience building and deploying enterprise‑grade agentic applications (e.g., LangGraph, LangChain agents)
Familiarity with scalable, enterprise‑level distributed systems
Experience with advanced data structures, algorithms, and complexity analysis
Demonstrated history of product value delivery
Education:
Bachelor’s degree in Computer Science, Computer Engineering, or a closely related quantitative field (required)
Master’s degree in Artificial Intelligence, Machine Learning, or a relevant field (strongly preferred)
Work authorization:
Must be a US Citizen, Green Card holder, or currently in the US with a valid H1B visa
Benefits
Competitive salary and benefits package
Flexible working arrangements (remote or hybrid options available)
The opportunity to work on life‑changing AI technology that directly impacts patient outcomes
Join a team that combines cutting‑edge innovation with a mission to save lives and improve health equity
Continuous learning opportunities with access to the latest tools and advancements in AI and healthcare
Location: New York, NY
#J-18808-Ljbffr
Experience working with the GCP Vertex AI ecosystem is essential. In this role you will design agents capable of complex reasoning and tool usage, leveraging Google's managed infrastructure (Vertex AI Vector Search, Cloud Run, and BigQuery) to ensure reliability, security, and performance.
Key Responsibilities
Architecting and implementing agentic workflows
Design autonomous loops: build stateful control loops (Perception → Reasoning → Action) where agents can interpret clinical data, plan necessary checks, and generate risk assessments
Conversational agentic workflow: chatbot‑style user experience powered by LLM
GCP integration: leverage Vertex AI for model serving and LLM reasoning, optimizing for long‑context windows to process complex medical history
RAG & grounding: implement “Enterprise Grounding” using Vertex AI Vector Search to ensure all agent outputs are strictly cited against official medical literature
Data & tool integration: build robust Python tools (function calling) that allow agents to securely query BigQuery or other datastores for patient demographics and symptoms
Security & compliance: ensure all AI operations comply with HIPAA/GDPR standards, implementing strict PII masking and data governance within Google Cloud
System reliability: deploy agents on Vertex AI, Cloud Run, or GKE, ensuring low‑latency inference and high availability for clinical users
Agent monitoring: implement effective AI agent execution monitoring and alert system to ensure SLA, safety, and security compliance
Leadership & strategy: guide a team of engineers in MLOps best practices (CI/CD for models, evaluation pipelines)
Evaluation: implement “LLM‑as‑a‑Judge” frameworks to automatically test agent accuracy against golden datasets of clinical cases
Required Technical Skills
Core AI: deep proficiency with LangChain or LangGraph, and specific experience with the Vertex AI SDK and ADK (Agent Development Kit)
Conversational workflow: Google Dialogflow CX
LLMs: expertise in prompting and configuring LLMs, specifically utilizing function calling and context caching
Experience integrating LLMs into platform and application workflow, with MCP protocols
RAG/embeddings: expert level experience in design and implementation of RAG‑based systems using embeddings and vector databases
Data engineering: strong SQL skills for BigQuery; experience with vector databases (Pinecone, Milvus, or Vertex Vector Search)
Backend engineering: mastery of Python (FastAPI) and containerization (Docker) for deploying microservices to Cloud Run or GKE
Healthcare domain: familiarity with handling unstructured medical text or clinical guidelines (highly preferred)
Qualifications
Experience:
5+ years of software development experience
2+ years of hands‑on experience building and deploying enterprise‑grade agentic applications (e.g., LangGraph, LangChain agents)
Familiarity with scalable, enterprise‑level distributed systems
Experience with advanced data structures, algorithms, and complexity analysis
Demonstrated history of product value delivery
Education:
Bachelor’s degree in Computer Science, Computer Engineering, or a closely related quantitative field (required)
Master’s degree in Artificial Intelligence, Machine Learning, or a relevant field (strongly preferred)
Work authorization:
Must be a US Citizen, Green Card holder, or currently in the US with a valid H1B visa
Benefits
Competitive salary and benefits package
Flexible working arrangements (remote or hybrid options available)
The opportunity to work on life‑changing AI technology that directly impacts patient outcomes
Join a team that combines cutting‑edge innovation with a mission to save lives and improve health equity
Continuous learning opportunities with access to the latest tools and advancements in AI and healthcare
Location: New York, NY
#J-18808-Ljbffr