Senior Software Engineer (AI Engineer)

Overview Fluxon is a product development team founded by ex-Googlers and startup founders. We offer full-cycle software development: from ideation and design to build and go-to-market. We partner with visionary companies, ranging from fast-growing startups to tech leaders like Google and Stripe, to turn bold ideas into products with the power to transform the world.

The role is open to candidates based in Poland preferably in Krakow, Wroclaw or Gdansk. About the role As an AI Engineer at Fluxon, you’ll take the lead in designing, building and deploying AI-powered applications for our clients. You'll be responsible for: System Architecture : Design and implement end-to-end AI systems and their parts, including data ingestion, preprocessing, model inference, and output structuring Generative AI Development : Build and optimize RAG (Retrieval-Augmented Generation) systems and Agentic workflows using frameworks like LangChain, LangGraph, ADK (Agent Development Kit), Genkit Production Engineering : Deploy models to production environments (AWS/GCP/Azure) using Docker and Kubernetes, ensuring high availability and scalability Evaluation & Monitoring : Implement feedback loops to evaluate model performance (accuracy, hallucinations, relevance) and set up monitoring for drift in production Collaboration : Work closely with other engineers to integrate AI endpoints into the core product and with product managers to define AI capabilities Model Optimization : Fine-tune open-source models (e.g., Llama, Mistral) for specific domain tasks and optimize them for latency and cost You'll work with technologies including: Languages Python (Preferred) AI / ML LangChain LangGraph Google ADK Genkit OpenAI API LLM - Large Language Model Platforms: Google Cloud Platform (GCP) or Amazon Web Services (AWS) Storage: Google Cloud Storage (GCS) or AWS S3 Firestore MongoDB Monitoring & Observability Qualifications 5+ years of industry experience in software engineering roles Strong understanding of Transformer architectures, embeddings, and vector similarity search Experience integrating with LLM provider APIs (OpenAI, Anthropic, Google Vertex AI) Hands-on experience with agent workflows like LangChain, LangGraph Experience with Vector Databases and traditional SQL / NoSQL databases Familiarity with cloud platforms, preferably GCP or AWS Understanding of patterns like RAG (Retrieval-Augmented Generation), few-shot prompting, and Fine-Tuning Solid understanding of software development practices including version control (Git) and CI/CD Nice to have: Experience with Google Cloud Platform (GCP) services, specifically Vertex AI, Firestore, and Cloud Functions Knowledge of prompt engineering techniques (Chain-of-Thought, ReAct, Tree of Thoughts) Experience building "Agentic" workflows where AI can execute tools or API calls autonomously What we offer Exposure to high-profile SV startups and enterprise companies Fully remote work with flexible hours Flexible paid time off Profit-sharing program Parental leave, including adoption and fostering Gym membership and tuition reimbursement #J-18808-Ljbffr