Requirements: English
Company: InPost
Region: Lublin , Lublin Voivodeship
We are seeking a skilled and innovativeAI Engineer with Full Stack Development expertisewho has experience working with Generative AI (GenAI) models, such as Large Language Models (LLMs), and implementing these solutions into web applications. This role combines the responsibilities of a full-stack developer with advanced knowledge of machine learning models, APIs, and cloud infrastructure, focusing on integrating state-of-the-art AI capabilities into user-friendly and efficient web-based applications.
Key Responsibilities:
Model Integration & API Development:
Integrate LLMs and other GenAI models into web applications through efficient API design and implementation.
Build and optimize API endpoints to allow seamless, real-time interaction between front-end applications and back-end AI models.
Design and develop secure, scalable, and high-performing microservices for AI model deployment.
Front-End Development:
Design and develop responsive and intuitive front-end applications usingReact.jsto enhance the user experience of AI-powered applications.
Implement front-end components to visualize, interpret, and manage AI model outputs effectively.
Back-End Development & AI Pipelines:
Develop robust back-end systems inPythonto support the deployment, scalability, and maintenance of GenAI models.
Build and maintain data pipelines, including preprocessing data and post-processing AI model outputs for consumption by applications.
Implement best practices for handling sensitive data and maintaining model performance.
Infrastructure & Deployment:
UseKubernetesandDockerfor containerization and orchestration to ensure scalable deployment and management of AI applications.
Implement continuous integration and continuous deployment (CI/CD) pipelines for automated testing and deployment of code changes.
Maintain a scalable and secure cloud infrastructure, leveraging platforms such asGoogle Cloud Platform, or Azurefor model training, storage, and deployment.
LLM and GenAI Ecosystem Expertise:
Utilizevector databases(e.g., Pinecone, Weaviate, or Faiss) to manage and retrieve embeddings for efficient similarity search and recommendation systems.
Work withframeworksfor model development and deployment, includingHugging Face Transformers, LangChain, and OpenAI.
Optimize and fine-tune LLMs to improve performance based on application needs.
Required Qualifications:
~ Min Bachelor''s degreein Computer Science, Engineering, or a related field.
~3+ yearsof experience as a full-stack developer, ideally with a focus on AI model integration.
~ Proficiency in Pythonfor backend development andReact.jsfor frontend development.
~ Strong knowledge of GenAI models and LLMs, including experience with model selection, tuning, and embedding strategies.
~ Experience withAPI development and integrationto facilitate communication between front-end applications and AI models.
~ Working knowledge ofcontainerization technologieslikeDockerandcontainer orchestrationwithKubernetes.
~ Familiarity withcloud platforms(AWS, GCP, or Azure) for AI model deployment and scalability.
~ Proficiency invector databasesand their integration with LLM models for enhanced application functionality.
~ Familiarity withdatabase management(SQL, NoSQL) andcaching solutions(e.g., Redis).
~ Experience inCI/CD pipelines, code versioning (Git), and DevOps practices.
~ Excellent knowledge ofEnglish AND Polish.
Preferred Qualifications:
Knowledge ofstreaming architecturesfor real-time data processing and ingestion (e.g., Apache Kafka).
Familiarity withserverless architectures(e.g., AWS Lambda) for scalable deployment of AI features.
Prior experience inML frameworkslike TensorFlow, PyTorch, or ONNX.
Understanding ofdata privacy and securitybest practices in AI applications.
Soft Skills:
Strongproblem-solvingskills and ability to work independently and as part of a team.
Excellentcommunication skillsto translate technical requirements into actionable development tasks.
Proactive approach to staying updated with emerging AI technologies and frameworks.
This is a unique opportunity to work on cutting-edge AI applications that leverage the latest advancements in Generative AI and Large Language Models, impacting the future of intelligent software development.