Lead AI Platform Engineer (Healthcare AI)

About Medsynapse

Medsynapse is a leading provider of RIS-PACS and Enterprise Imaging solutions serving hospitals, diagnostic centers and teleradiology networks globally. We are building the next generation of AI-enabled radiology workflow solutions that combine Large Language Models (LLMs), medical AI, RIS-PACS workflows and clinical data to improve radiologist productivity and patient care.

We are looking for a highly motivated Lead AI Platform Engineer to architect and build our Healthcare AI platform.

Role Overview

As Lead AI Platform Engineer, you will be responsible for designing and developing the AI orchestration layer that powers our future AI-enabled workflow products. You will work at the intersection of AI, healthcare, cloud platforms and enterprise imaging systems. This is a hands-on technical leadership role involving architecture, coding, mentoring and product innovation.

Key Responsibilities

AI Platform Development

• Design and develop scalable AI platform architecture.
• Build Retrieval-Augmented Generation (RAG) systems for clinical applications.
• Integrate LLMs into radiology workflows.
• Develop AI agents and workflow orchestration pipelines.
• Implement prompt management and evaluation frameworks.

Healthcare Integration

• Integrate AI services with RIS, PACS, VNA and reporting systems.
• Build services utilizing DICOM, HL7 and FHIR standards.
• Develop secure access to patient records and imaging metadata.

Product Development

• Work closely with radiologists and product teams.
• Translate clinical requirements into AI-powered solutions.

Technical Leadership

• Define engineering best practices.
• Mentor software engineers and AI developers.
• Establish architecture standards and code review processes.
• Evaluate emerging AI technologies and frameworks.

Required Skills

Programming

• Python (expert level)
• FastAPI
• RESTful APIs
• PostgreSQL

AI & LLM Technologies

• OpenAI, Anthropic, Gemini or equivalent LLM platforms
• Retrieval-Augmented Generation (RAG)
• Vector databases
• Embeddings
• Prompt engineering
• AI evaluation frameworks

Cloud & Infrastructure

• Docker
• Kubernetes
• CI/CD pipelines
• Linux

Data Technologies

• PostgreSQL
• Redis
• Vector databases such as Qdrant, Weaviate, Pinecone or pgvector

Preferred Skills

• Experience with healthcare systems
• DICOM, HL7, FHIR knowledge
• PACS or RIS domain experience
• LangGraph, LangChain, LlamaIndex or similar frameworks
• Experience building enterprise AI products
• Understanding of healthcare compliance and security

Experience

• 5-10 years of software engineering experience
• 2+ years of practical LLM/Generative AI experience
• Experience leading technical projects or teams