Position : Backend AI / ML Engineer (with Full Stack Expertise)
Experience : 3–8
Type : Fulltime| Hybrid
About the Role
This role transcends traditional backend development. We’re seeking a highly skilled Backend AI / ML Engineer with strong Python expertise and a working understanding of Full Stack systems.
You’ll architect and scale backend infrastructures that power our AI-driven products, while also collaborating across frontend, blockchain, and data science layers to deliver end-to-end, production-grade solutions.
You will engineer the backbone for advanced AI ecosystems — building robust RAG pipelines, autonomous AI agents, and intelligent, integrated workflows. Your work will bridge the gap between foundational ML models and scalable, high-performance applications.
Key Responsibilities
- Design, develop, and deploy high-performance, asynchronous APIs using Python and FastAPI.
- Ensure scalability, security, and maintainability of backend systems powering AI workflows.
- Build and manage multi-step AI reasoning frameworks using Langchain and Langgraph for stateful, autonomous agents.
- Implement context management, caching, and orchestration for efficient LLM performance.
- Architect full Retrieval-Augmented Generation (RAG) systems — including data ingestion, embedding creation, and semantic search across vector databases such as Pinecone, Qdrant, or Milvus.
- Construct autonomous AI agents capable of multi-step planning, tool usage, and complex task execution.
- Collaborate with data scientists to integrate cutting-edge LLMs into real-world applications.
- Implement system and process automation using n8n (preferred) or similar platforms.
- Integrate core AI services with frontend, blockchain, or third-party APIs through event-driven architectures.
Required Skills & Qualifications
Expert-level Python for scalable backend system development.Strong experience with FastAPI, async programming, and RESTful microservices.Deep hands-on experience with Langchain and Langgraph for LLM workflow orchestration.Proficiency in Vector Databases (Pinecone, Qdrant, Milvus) for semantic search and embeddings.Production-level RAG implementation experience.Experience integrating ML models with backend APIs.Strong understanding of containerization (Docker, Kubernetes) and CI / CD workflows.Excellent problem-solving, architecture, and debugging skills