AI Engineer

About the role

Snapp is hiring an AI Engineer in Tehran to build scalable AI solutions that improve user experiences, automate operations and address real business needs. The work covers Agentic AI, intelligent search, speech processing and foundation-model-based applications, taking ownership of AI projects end-to-end, from research and prototyping through evaluation, deployment and continuous improvement.

Key responsibilities

• Collaborate with product, engineering and operations teams to turn business needs into well-defined technical problems and measurable success criteria.
• Design, build and deploy LLM-powered applications and AI agents, including conversational workflows, tool and API integrations, retrieval mechanisms, state management and error recovery.
• Select, evaluate and adapt foundation models using prompt engineering, retrieval-augmented generation (RAG) and fine-tuning.
• Contribute to semantic and hybrid search, ranking, reranking and speech-related initiatives.
• Design evaluation datasets and reproducible experiments to measure model quality and system performance.
• Analyze system failures and error patterns, and write clean, maintainable production-quality code.
• Optimize model quality, latency, inference costs and resource utilization, and implement safeguards for data privacy, access control and AI agent actions.

Required profile

• Bachelor's degree or higher in Computer Science, Computer Engineering, Artificial Intelligence or a related field.
• At least 3 years of experience in AI engineering, machine learning or software engineering focused on AI-powered products.
• Hands-on experience building and deploying at least one machine learning or foundation-model-based solution in a real-world environment.
• Ability to build evaluation datasets, analyze errors and distinguish data, model and system-level issues.

Required skills

• Strong Python and solid software engineering fundamentals (modular design, version control, testing, debugging, API integration).
• Understanding of machine learning and deep learning, including Transformers, embeddings and model evaluation.
• Practical experience with LLMs, RAG, tool calling and agentic workflows.
• Experience with a major deep learning framework such as PyTorch and tools for pretrained models.
• Familiarity with Linux, Docker and service deployment and monitoring.
• English reading of technical documentation and research papers.