AI Engineer

As an AI Engineer, you will build scalable AI solutions that improve user experiences, automate operations, and address real business needs. Our work spans Agentic AI, intelligent search, speech processing, and foundation-model-based applications. You will take ownership of AI projects end-to-end, from research and prototyping to evaluation, deployment, and continuous improvement.

• Collaborate with product, engineering, and operations teams to translate business needs into well-defined technical problems, measurable success criteria, and actionable implementation plans.

• 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 appropriate techniques such as prompt engineering, retrieval-augmented generation (RAG), and fine-tuning.

• Contribute to semantic and hybrid search, ranking, reranking, and speech-related initiatives based on team and business priorities.

• Design evaluation datasets and reproducible experiments to measure model quality and end-to-end system performance.

• Investigate system failures, analyze error patterns, and identify opportunities for improvement across data, models, prompts, tools, and system architecture.

• Write clean, maintainable, production-quality code and contribute to deployment, monitoring, troubleshooting, and ongoing system maintenance.

• Optimize model quality, latency, inference costs, and resource utilization within product and infrastructure constraints.

• Document technical decisions, participate in code reviews, and share knowledge and best practices across the team.

• Implement appropriate safeguards for data privacy, access control, and AI agent actions.

• Bachelor’s degree or higher in Computer Science, Computer Engineering, Artificial Intelligence, or a related technical field.

• At least 3 years of relevant professional 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.

• Strong Python programming skills and solid software engineering fundamentals, including modular design, version control, testing, debugging, and API integration.

• Good understanding of machine learning and deep learning fundamentals, including Transformers, embeddings, and model evaluation.

• Practical experience working with large language models (LLMs) and a solid understanding of RAG, tool calling, and agentic workflows.

• Ability to build evaluation datasets, analyze errors, and distinguish between data-related, model-related, and system-level issues.

• Experience with a major deep learning framework, such as PyTorch, and tools for working with pretrained models.

• Familiarity with Linux, Docker, and the fundamentals of service deployment and monitoring.

• Ability to read technical documentation and research papers in English and apply relevant findings to practical engineering problems.

• Strong problem-solving, analytical thinking, independent learning, communication, and collaboration skills.

• A strong sense of ownership and the ability to navigate ambiguity, make informed technical decisions, and deliver results.

Experience in one or more of the following areas is a plus:

• Building production-ready AI agents with multiple tools, state management, and robust failure recovery.

• Working with open-source or open-weight models, fine-tuning, model serving, and inference optimization.

• Developing search, retrieval, ranking, reranking, or recommendation systems.

• Working with automatic speech recognition (ASR), text-to-speech (TTS), audio processing, or real-time conversational AI systems.

• Working with Persian-language data and addressing language-specific modeling and evaluation challenges.

• Building high-traffic services, asynchronous processing pipelines, or systems running on GPU infrastructure.