• Design, develop, and maintain scalable Python-based APIs and backend services using FastAPI and related frameworks • Build, deploy, and optimize production-grade LLM applications using providers such as OpenAI and Anthropic • Design and implement end-to-end RAG solutions, including vector databases, semantic search, retrieval optimization, and chunking strategies • Develop and manage secure, scalable MCP servers and AI infrastructure • Build and orchestrate multi-agent systems to automate complex workflows and business processes • Create, test, and refine prompts, agent instructions, and LLM interactions to improve solution quality and performance • Leverage AI-assisted development tools (e.g., Claude Code, Cursor, GitHub Copilot) to accelerate software delivery and engineering efficiency • Implement event-driven architectures, messaging systems, and real-time communication patterns • Monitor, troubleshoot, and optimize AI and backend systems for performance, reliability, scalability, and security • Collaborate with cross-functional teams to deliver innovative AI solutions and establish engineering best practices.

• Design, develop, and maintain scalable Python-based APIs and backend services using FastAPI and related frameworks • Build, deploy, and optimize production-grade LLM applications using providers such as OpenAI and Anthropic • Design and implement end-to-end RAG solutions, including vector databases, semantic search, retrieval optimization, and chunking strategies • Develop and manage secure, scalable MCP servers and AI infrastructure • Build and orchestrate multi-agent systems to automate complex workflows and business processes • Create, test, and refine prompts, agent instructions, and LLM interactions to improve solution quality and performance • Leverage AI-assisted development tools (e.g., Claude Code, Cursor, GitHub Copilot) to accelerate software delivery and engineering efficiency • Implement event-driven architectures, messaging systems, and real-time communication patterns • Monitor, troubleshoot, and optimize AI and backend systems for performance, reliability, scalability, and security • Collaborate with cross-functional teams to deliver innovative AI solutions and establish engineering best practices

• Design, develop, and maintain scalable Python-based APIs and backend services using FastAPI and related frameworks. • Build, deploy, and optimize production-grade LLM applications using providers such as OpenAI and Anthropic. • Design and implement end-to-end RAG solutions, including vector databases, semantic search, retrieval optimization, and chunking strategies. • Develop and manage secure, scalable MCP servers and AI infrastructure. • Build and orchestrate multi-agent systems to automate complex workflows and business processes. • Create, test, and refine prompts, agent instructions, and LLM interactions to improve solution quality and performance. • Leverage AI-assisted development tools (e.g., Claude Code, Cursor, GitHub Copilot) to accelerate software delivery and engineering efficiency. • Implement event-driven architectures, messaging systems, and real-time communication patterns. • Monitor, troubleshoot, and optimize AI and backend systems for performance, reliability, scalability, and security. • Collaborate with cross-functional teams to deliver innovative AI solutions and establish engineering best practices.

Role Description Join our Data & AI team as a Junior AI Engineer, where you will work on end-to-end projects for clients across various industries, including manufacturing, finance, healthcare, and media. You will design, build, and deploy AI systems within the AWS ecosystem, providing opportunities to grow by rotating between diverse initiatives. - A large-scale multi-tenant AI voicebot making hundreds of thousands of outbound calls monthly. - An internal AI Agents platform for a 10,000+ employee manufacturing enterprise. - Document processing pipelines: automated OCR, classification, and metadata extraction. - An end-to-end media solution: video scene analysis, product matching with LLM ranking, and automated marketing asset generation for a global broadcaster. Projects range from a few weeks (PoC, MVP) to many months or years (production deployments). Client scale varies from mid-sized Polish companies to international enterprises. Tech stack includes: - Cloud: AWS (Bedrock, SageMaker, Lambda, Step Functions, S3, DynamoDB, Bedrock AgentCore) - IaC: Terraform - Languages: Python - AI/agent frameworks: LangGraph, Pipecat (Strands Agents, CrewAI, or Haystack are a plus) - Observability: LangFuse - AI-native development: Cursor, Claude Code, Codex (licenses provided) - CI/CD: GitHub Actions, CodePipeline Your Responsibilities: - Design, implement, and test AI solutions within the AWS ecosystem. - Build agentic AI applications using frameworks such as LangGraph and Strands Agents. - Integrate AI solutions with clients’ existing technology stacks and systems. - Develop and maintain automation for model training, deployment, and CI/CD pipelines. - Support presales activities from a technical perspective, including co-authoring proposals and Statements of Work (SoW). - Collaborate in small, agile project teams (2–5 people), often working directly with clients. Qualifications - 2+ years of experience in AI/ML and strong Python skills, with the ability to write production-grade code. - Hands-on experience with AI models (fine-tuning, prompt engineering, RAG, API integrations) and familiarity with at least one agentic framework (e.g. LangGraph, CrewAI, Haystack, Strands Agents). - Experience using AI-native development tools (e.g. Cursor, Claude Code, Codex) in day-to-day work. - Solid software engineering practices (code reviews, Git, testing, deployment) and AWS knowledge or willingness to quickly ramp up. - Consultative mindset: understanding client problems and proposing solutions, not just executing tasks. - Self-driven, open to feedback, and proactive in identifying and addressing issues early. - Team-oriented approach, including active knowledge sharing as a standard way of working. - Fluency in both English and Polish, written and spoken. Requirements - Experience in Computer Vision (e.g. OpenCV, detection and segmentation models) is a plus. - Familiarity with Infrastructure as Code tools (e.g. Terraform) is a plus. - Experience with voice-based solutions (voicebots, speech-to-text, text-to-speech) is a plus. - Background in a consulting or software house environment is a plus. - Hands-on experience with AWS AI services such as Amazon Bedrock or SageMaker is a plus. Benefits - Continuous learning and growth through internal training, knowledge-sharing sessions, and hands-on learning from real projects. - Training budget for certifications, courses, and professional development aligned with your career goals. - Comprehensive private healthcare to help you stay healthy and focused. - Multisport card co-financing to encourage staying active. - Access to a language learning platform to improve your language skills at your own pace. - Flexible working hours & remote work options. - Company events for integration and fun.