Senior Backend Engineer (Python) | WFH, Midshift
Summary
Builds and scales Python/FastAPI backend services that integrate LLMs, RAG pipelines, and vector databases for an AI-driven healthcare market-research platform.
GRG Health is a global leader in healthcare professional (HCP) market research, data, and engagement, building AI-driven platforms for global pharmaceutical and life sciences organizations.
Role Overview
This role is responsible for building and scaling the backend services that power GRG Health's AI and LLM-driven features. The AI Backend Engineer integrates LLMs, RAG pipelines, and vector databases into production-grade APIs, working across the AI and data stack to deliver intelligent, reliable, and scalable systems.
Key Responsibilities
- Develop backend services and APIs using Python and FastAPI for AI-driven features
- Integrate LLMs, embeddings, and RAG pipelines into production systems
- Build and consume APIs for AI services, agents, and data-intensive workflows
- Work with PostgreSQL, MongoDB, and vector databases for AI applications
- Implement authentication, authorization, and security best practices
- Optimize the performance, reliability, and scalability of AI backend services
- Collaborate with AI/ML, data, and frontend teams to deliver end-to-end AI features
- Contribute to deployment, monitoring, and observability of AI systems on cloud infrastructure
Required Experience & Skills
- 3+ years of backend engineering experience with Python
- Strong expertise in FastAPI and REST API design
- Hands-on experience integrating LLM APIs and building RAG pipelines
- Experience with vector databases (Pinecone, Weaviate, Chroma, FAISS, etc.)
- Working knowledge of PostgreSQL and MongoDB
- Familiarity with LLM orchestration frameworks such as LangChain or LangGraph
- Understanding of cloud-native deployments, scalability, and distributed systems
Work Culture & Expectations
- Startup-lean environment with enterprise-grade engineering standards
- High-ownership role with accountability for architecture, delivery, and outcomes
- AI-first product stack with real-world production usage
- Strong bias toward execution, clarity, and technical excellence
- Engineers are expected to take end-to-end responsibility for systems and outcomes
Location: Metro Manila
Work Arrangement: Hybrid (1-2 times a month on-site required)
Schedule: Monday - Friday, 11:30AM - 8:30PM