Every cancer patient deserves access to treatment options. Massive Bio is an AI-powered precision medicine platform transforming how cancer patients discover and access clinical trials by eliminating the barriers of geography, financial constraints, and information asymmetry that have historically limited enrollment.
Founded in 2015 and headquartered in US, Massive Bio is scaling its impact globally by powering operations across multiple countries and bringing innovative cancer treatment options to a rapidly growing and diverse population of patients. Through our proprietary AI platform, we connect individuals to clinical trials worldwide and partner with leading pharmaceutical companies, contract research organizations (CROs), and healthcare systems to accelerate drug development and expand equitable access to cutting-edge therapies.
We're looking for an AI Developer to join our engineering team and build intelligent healthcare agents on our Agent Studio platform. You'll design, develop, and deploy AI-powered microservices that process medical records, match patients to clinical trials, and integrate with healthcare data standards, all within a modern, event-driven architecture.
This is a hands-on engineering role where you'll write production code daily, work with LLMs, vector databases, and healthcare data formats, and ship features that directly impact patient outcomes.
What You'll Do
Build AI agents as Python microservices using our SDK (massivebio-agent-sdk)
Design and implement multi-agent pipelines for medical data processing (OCR, clinical abstraction, terminology mapping, FHIR generation)
Integrate LLMs (GPT-4o, GPT-5) for clinical text extraction, summarization, and decision support
Work with vector databases (Qdrant) for semantic search, RAG, and terminology resolution
Build and maintain integrations with healthcare systems (Azure FHIR, HL7, SNOMED CT, RxNorm, LOINC)
Develop dashboard features for agent management, monitoring, and deployment
Write clean, tested, production-ready code with proper error handling and observability
Collaborate with clinical teams to translate medical workflows into agent pipelines
Requirements
Must Have:
3+ years of professional software development experience
Professional proficiency in English, both written and spoken.
Strong Python skills (async/await, Pydantic, FastAPI or similar frameworks)
Experience with LLMs prompt engineering, function calling, RAG pipelines, or fine-tuning
REST API design and implementation
SQL proficiency (PostgreSQL preferred)
Git workflow (branching, PRs, code review)
Comfortable with Docker and containerized deployments
Strong problem-solving skills and ability to work independently
Nice to Have:
Experience with healthcare data (FHIR, HL7, ICD-10, SNOMED CT, medical records)
Azure cloud services (Container Apps, Service Bus, Cosmos DB, Key Vault, Blob Storage)
Vector databases (Qdrant, Pinecone, Weaviate) and embedding models
OpenTelemetry or distributed tracing experience
TypeScript/React (Next.js) for dashboard frontend contributions
Experience building event-driven architectures (message queues, pub/sub)
CI/CD pipelines (Azure DevOps, GitHub Actions)
Knowledge of clinical trials, oncology workflows, or biotech domain
Experience with CRM integrations (HubSpot, Salesforce)
Tech Stack
Language: Python 3.12, TypeScript
Backend: FastAPI, Pydantic v2, asyncio
Frontend: Next.js 15, React 19, Tailwind CSS
AI/ML: GPT-4o/5, Azure OpenAI, LLM Gateway, RAG
Databases: PostgreSQL, Cosmos DB (MongoDB API), Qdrant
Messaging: Azure Service Bus (queues, topics)
Healthcare: Azure FHIR (R4), SNOMED CT, RxNorm, LOINC
Infrastructure: Azure Container Apps, Docker, Azure DevOps CI/CD
Observability: OpenTelemetry, Azure Monitor
Package Management: uv, Azure Artifacts (private PyPI)
How You'll Work
Agents as microservices — each agent is a standalone Python service that extends BaseAgent and implements a single process() method
Built-in platform services — agents access LLM Gateway, Vector DB, PostgreSQL, HubSpot CRM, and FHIR Server via SDK clients (self.llm, self.vectordb, self.postgres, etc.)
Event-driven pipelines — agents communicate via Azure Service Bus queues and topics
One-click deployment — push code to GitHub, deploy from the Agent Studio dashboard
Full observability — execution tracking, token usage monitoring, distributed tracing across agent pipelines
Job details are sourced from the employer's original posting.
Open job postingAbout the company
Massive Bio is a company focused on revolutionizing cancer treatment through AI-powered solutions.