About SnappPay

SnappPay is the first and leading BNPL provider in Iran, started in 2020. We are leveraging Financial Technologies to reshape Iranians’ experience of consumer credit.
Supporting Snapp Group’s mission of enhancing Iranian people's quality of life through Internet services, SnappPay’s mission is to bring financial freedom to all Iranians by providing them with better, smarter, and more efficient solutions for payment and shopping.

About the Role

The AI Engineer will play a key role in designing, developing, and deploying production-grade AI solutions across our business ecosystem. The role leverages Large Language Models (LLMs) and Agentic AI frameworks to build intelligent conversational systems, autonomous AI agents, and Retrieval-Augmented Generation (RAG) pipelines. This role is responsible for architecting scalable AI services, driving technical innovation, and collaborating closely with Product, Engineering, and Data teams to deliver high-impact solutions that elevate customer experience and operational efficiency.

Responsibilities

• Design, implement, and optimize LLM-powered applications including chatbots, AI assistants, and autonomous agents.
• Build production-ready RAG pipelines using vector databases, embeddings, and enterprise knowledge sources.
• Develop AI agents capable of planning, reasoning, and tool calling using modern agent frameworks.
• Fine-tune, evaluate, and optimize open-source and commercial LLMs for business use cases.
• Design scalable AI microservices and REST APIs for production deployment.
• Collaborate with Data Scientists, Product Managers, and Software Engineers to deliver AI products.
• Monitor, evaluate, and continuously improve LLM quality, latency, reliability, and cost efficiency.
• Stay current with the latest advancements in LLMs, Agentic AI, reasoning models, and AI infrastructure.

Requirements

• Strong experience with Python.
• Strong understanding of Large Language Models (GPT, Llama, Qwen, DeepSeek, Gemma, etc.).
• Hands-on experience with Retrieval-Augmented Generation (RAG).
• Experience with Vector Databases such as Milvus, Qdrant, Weaviate, Pinecone, FAISS, or Chroma.
• Experience with Agent Frameworks such as LangGraph, CrewAI, AutoGen, Pydantic, or similar.
• Experience with Prompt Engineering and structured output generation.
• Experience deploying AI applications using FastAPI or similar frameworks.

Nice to Have

• Fine-tuning LLMs using LoRA, QLoRA, PEFT.
• Model evaluation and benchmarking.
• Experience with multi-agent systems.
• Experience building enterprise AI applications.
• Experience with Docker and containerized deployment.
• Familiarity with Git and CI/CD workflows.