RapidBrains
Website:
rapidbrains.com
Job details:
Role Objective
We are looking for a heavy-hitting Backend Developer to architect the next generation of our AI ecosystem. You won't just be "using" LLMs; you will be building the infrastructure that allows them to communicate, use tools, and interact with enterprise data using the Model Context Protocol (MCP) and Multi-Agent Orchestration.
Key Responsibilities
- Architect MCP Infrastructure: Design and implement production-ready MCP Servers and Clients to standardize how our AI models interact with secure data sources and local tools.
- High-Performance Backend: Build and optimize asynchronous APIs using Python (3.11+) and FastAPI, ensuring sub-100ms latency for real-time agentic workflows.
- Agentic Orchestration: Develop intelligent routing systems, tool-calling logic, and "Agent-to-Agent" (A2A) communication patterns using frameworks like LangGraph or CrewAI.
- Production MLOps: Deploy scalable AI services on AWS (EKS/Lambda) using Docker and Kubernetes, ensuring robust CI/CD pipelines and monitoring.
- Data Strategy: Implement Advanced RAG (Retrieval-Augmented Generation) pipelines involving hybrid search, semantic chunking, and vector databases (Qdrant/Pinecone/Milvus).
Technical Skill Set
- Core Backend: Expert-level Python (AsyncIO, Type Hinting, Pydantic) and FastAPI.
- AI Standards: Hands-on experience with Model Context Protocol (MCP) and LLM Orchestration.
- Cloud & DevOps: Strong proficiency in AWS services, Docker, Kubernetes, and Terraform/Ansible.
- Database & Search: Experience with PostgreSQL, Redis, and Vector Databases.
- Messaging: Familiarity with event-driven architectures using Kafka, RabbitMQ, or Celery.
Preferred Qualifications
- Contributed to open-source AI projects or built custom MCP servers.
- Deep understanding of LLM Evaluation (DeepEval/Ragas) and observability.
- Experience in high-compliance domains (Fintech/Healthcare) is a plus.
Click on Apply to know more.