InPost Group is looking for an AI Principal Software Engineer to lead the integration of Generative AI models into our business applications. This role combines software engineering expertise with deep knowledge of LLMs, APIs, and cloud infrastructure to build modern, AI-enhanced systems.
What You'll Do
- Drive the technical architecture across the domain, focusing on modernization, scalability, and AI integration.
- Lead the design and implementation of microservices and cloud-native systems.
- Guide the transition from legacy systems to modern distributed systems.
- Collaborate with senior stakeholders to align on technology direction.
- Champion engineering excellence, fostering a culture of autonomy, accountability, and quality.
- Provide mentorship and leadership across engineering teams.
- Integrate LLMs and other GenAI models into web applications through efficient API design.
- Build and optimize API endpoints for real-time communication between front-end applications and back-end AI services.
- Design and develop secure, scalable, and high-performing Java-based microservices for AI model deployment.
- Develop robust back-end systems in Java to support deployment, scalability, and maintenance of GenAI models.
- Build and maintain data pipelines, including preprocessing input data and post-processing model outputs.
- Implement best practices for sensitive data handling and maintaining high model performance.
- Use Kubernetes and Docker for containerization and orchestration of AI applications.
- Implement CI/CD pipelines for automated testing and delivery of code changes.
- Maintain scalable and secure cloud infrastructure using platforms like Google Cloud Platform or Azure for model training, storage, and deployment.
- Utilize vector databases for embedding management and similarity search.
- Work with frameworks supporting model development and deployment, including Hugging Face, LangChain, and the OpenAI ecosystem.
- Optimize and fine-tune LLMs based on specific application needs.
What We're Looking For
- Bachelor’s degree in Computer Science, Engineering, or a related field.
- 7+ years of relevant experience, ideally with a focus on AI model integration.
- Proficiency in Java for backend development.
- Strong knowledge of GenAI/LLMs, including model selection, tuning, and embedding strategies.
- Experience developing APIs enabling communication between front-end applications and AI systems.
- Working knowledge of Docker and Kubernetes.
- Familiarity with cloud platforms (AWS, GCP, Azure) for scalable AI deployment.
- Experience with vector databases and their integration with LLM-driven applications.
- Familiarity with SQL and NoSQL databases, as well as caching solutions.
- Experience with CI/CD pipelines, Git, and DevOps practices.
- Excellent command of English AND Polish.
Nice to Have
- Knowledge of streaming architectures for real-time data processing.
- Familiarity with serverless architectures for scalable AI features.
- Prior experience with ML frameworks such as TensorFlow, PyTorch, or ONNX.
- Strong understanding of data privacy and security in AI applications.
Technical Stack
- Backend & AI: Java, Generative AI, LLMs, Microservices, APIs
- Infrastructure: Cloud-native, Docker, Kubernetes, CI/CD, Google Cloud Platform, Azure, AWS
- Data & Tools: Vector Databases, Hugging Face, LangChain, OpenAI, SQL, NoSQL, Redis, Git
- Additional: Apache Kafka, TensorFlow, PyTorch, ONNX
Team & Environment
You will collaborate with senior stakeholders, including Engineering Managers, Staff and Principal Engineers, and Directors, in a diverse, international, and cross-functional environment.
Benefits & Compensation
- The option to work from the office or 100% remotely.
- Opportunity to work with leading experts in a diverse, international and cross-functional environment.
- Fulfilling careers with a range of benefits and investment in training opportunities.
- Involvement in technology monitoring and choices.
- Your impact will be visible instantly and you will be making a difference in our users lives.
- Participation in building new Centre of Excellence at InPost.
Work Mode
This role offers a hybrid work model.
InPost Group is an equal opportunity employer.
