Artificial Intelligence Engineer

Job Title: Generative AI Developer

Location: Warsaw, Poland (Hybrid: 2-3 Days to Office in a Week)

Duration: 6 Months (Extendable)

Employment Type: Contract B2B

Roles & responsibilities:

Mandatory Skills:

GenAI, LLMs, RAG, Python, Java, or Scala, REST APIs, Kafka, and cloud platforms (AWS/Azure)

Desired Skills:

Docker, Kubernetes, CI/CD, Git, and exposure to prompt engineering, embeddings, or AI-based toolchains preferred

• Designing and implementing backend systems to support Generative AI workflows and services.
• Developing microservices and APIs that integrate with GenAI models, vector databases, and orchestration tools (e.g., LangChain, LangGraph).
• Building scalable infrastructure for deploying and serving LLMs and AI pipelines in production environments.
• Creating and maintaining data pipelines to support GenAI use cases, including prompt data processing and model feedback loops.
• Participating in architecture reviews focused on optimizing GenAI system performance, latency, and modularity.
• Collaborating with AI/ML engineers to enable plug-and-play components (e.g., Intent Resolver, Tool Agent, LLM Gateway) in agentic workflows.
• Debugging, profiling, and optimizing GenAI applications, including prompt execution paths, model inference, and external API integration.
• Writing technical documentation related to GenAI service design, deployment procedures, and best practices.
• 5+ years of total experience in IT
• 1+ years of hands-on experience with GenAI technologies — including LLMs, prompt engineering, embeddings, fine-tuning, or building RAG (Retrieval-Augmented Generation) pipelines.
• Strong programming skills in one or more languages such as Python, Java, or Scala, with a solid foundation in software design principles, testing, and version control (e.g., Git). Python developers are preferred.
• Strong backend engineering background with expertise in building scalable systems using Python, C#, Java or similar, and hands-on experience with microservices, REST APIs, Kafka, and cloud platforms (AWS/Azure) — preferably with exposure to secure, low-latency architectures.
• Demonstrated interest or experience in GenAI/Agentic AI systems — including building or integrating with LLMs (e.g., OpenAI, Claude), use of tools like LangChain, LangGraph, Copilot, or vector DBs, or implementing AI agent orchestration logic in real-world workflows.
• Comfortable working in AI-first environments, with experience using modern developer tools (e.g., Docker, Kubernetes, CI/CD, Git), and exposure to prompt engineering, embeddings, or AI-based toolchains preferred.