AI ENGINEER

AI Engineer

Debales.ai

Work from home / Remote

Experience Required: 02+ Years (Relevant AI/LLM Experience)

Employment Type: Full-Time

About the Role

We are looking for a skilled AI Engineer to design and build scalable LLM-based systems and multi-agent architectures. The ideal candidate has hands-on experience with LangGraph and has built production-ready AI solutions.

Key Responsibilities

1. Architect and develop LLM-based AI applications and multi-agent workflows.
2. Use LangGraph to build multi-agentic, customizable, and stateful AI architectures.
3. Design modular agent systems with tool integration, memory handling, and workflow orchestration.
4. Build and deploy AI agents in production environments.
5. Develop and optimize RAG pipelines using embeddings and vector databases.
6. Integrate AI systems with internal APIs and third-party services.
7. Implement evaluation frameworks and observability tooling for monitoring performance.
8. Collaborate with product, backend, and DevOps teams to ship scalable AI systems.

Required Skills & Experience

• Strong proficiency in Python
• Hands-on experience with LangGraph (mandatory)
• Experience with LangChain or similar agent frameworks
• Proven ability to build multi-agent customizable architectures
• At least 2 AI/LLM-based projects (preferably involving agent systems or RAG pipelines)
• Solid understanding of LLM architecture, transformers, and prompt engineering
• Experience with embeddings and vector databases (FAISS, Pinecone, Weaviate, etc.)
• Experience deploying AI systems in production
• Familiarity with Docker and cloud platforms (AWS/GCP/Azure preferred)

Good to Have

• Experience with AI observability tools (Langfuse, OpenTelemetry, W&B)
• Knowledge of system design and scalable backend architecture
• Understanding of evaluation frameworks for LLM applications