We are looking for a skilled Senior AI Engineer who is equally passionate about modern artificial intelligence and solid software engineering. In this role, you will be a core technical contributor focused on building scalable, production-grade AI systems.
Rather than just making simple API calls, you will build complex AI software using modern NLP techniques, autonomous agent architectures, and RAG pipelines. You will bring strong backend engineering habits—writing clean Python code, building fast APIs, optimizing databases, and designing resilient system architectures.
Job Description Develop and deploy software pipelines utilizing Large Language Models (LLMs), embeddings, and information retrieval techniques to solve real-world problems. Architect and implement autonomous and semi-autonomous AI agents, utilizing tool-calling, multi-step reasoning, and structured state management. Architect and implement autonomous and semi-autonomous AI agents, utilizing tool-calling, multi-step reasoning, and structured state management. Build effective Retrieval-Augmented Generation systems, integrating semantic search, hybrid retrieval, and re-ranking to ensure high accuracy. Design and maintain asynchronous, low-latency APIs and microservices using Python and FastAPI, adhering to software engineering best practices (clean code, modularity, testing). Work deeply with both relational databases (PostgreSQL) and Vector Databases (e.g., Qdrant, Milvus, pgvector). You will handle query optimization, schema design, and indexing to eliminate performance bottlenecks. Collaborate with the team on distributed system design, ensuring our AI infrastructure is scalable, fault-tolerant, and efficient. Utilize Docker for containerization and maintain robust, collaborative version control workflows using Git.
Requirements 2+ years of commercial experience developing AI/ML software pipelines, with a focus on modern NLP and LLM-powered applications. Proven track record as a software engineer with high proficiency in Python, RESTful API design (FastAPI), and modern software development practices. Practical, hands-on experience with:
Agent Design: Tool usage, LLM orchestration, and workflow routing
RAG & Information Retrieval: Embeddings, vector spaces, and search optimization.
Prompt Engineering & Model API Integration.
Hands-on experience with PostgreSQL and at least one major Vector Database, including practical skills in query tuning, data caching, and index optimization. Strong understanding of how to integrate AI components into larger, scalable backend systems. Comfortable working with Docker and Git in daily development.
Nice to Have Experience with LLM observability, tracing, and evaluation frameworks (e.g., LangSmith, Ragas, Phoenix).Practical knowledge of utilizing pgvector within high-load PostgreSQL environments.Experience with asynchronous message queues (e.g., Redis, Celery, RabbitMQ) for background AI processing.Fine-tuning NLP and audio models (LLMs, STT, TTS, Encoder-only models, etc.).Familiarity with Kubernetes
گروه شرکتهای همکاران سیستم در سال 1366 با هدف بهره گیری از فناوری اطلاعات برای کمک به پیشبرد بهتر کسبوکارها شکل گرفت و در حال حاضر به عنوان بزرگترین مجموعه دانش بنیان کشور در زمینهی تولید نرمافزار و ارائهی راهکارهای تخصصی به فعالیت خود ادامه میدهد.