AI Engineer
Krakow, Poland, Kraków
INFOPLUS TECHNOLOGIES
· Job Title: AI Engineer
· Location: Krakow (3 days onsite)
· Duration: Contract
** NOTE: 3 days/week onsite work is mandate for this role **
Job Description:
Experience
(must)
Python, LLM, Prompt engineering, Vector databases, RAG architecture, Agentic libraries(Lang chain/Lang graph/Autogen), Computer Vision, Document Processing
MUST HAVE JD SKILLS as below
Solid understanding of API integration patterns and inter-servic communication (e.g. REST, Kafka)
Experience with authentication and authorization mechanisms (e.g. OAuth2, JWT, Azure AD)
At least two ML/AI solutions delivered to production, ideally involving document understanding, NLP or search/retrieval systems
Practical knowledge and hands-on experience with: RAG architectures, LLMs (e.g., OpenAI, Antropic), Vector databases (e.g., FAISS, Azure AI Search), Embeddings (e.g., OpenAI)
Strong grasp of NLP techniques: named entity recognition (NER), document classification, chunking, summarization, question answering.
Ability to evaluate trade-offs and select appropriate ML/AI techniques for a given problem.
Experience with PoC development and iterating quickly based on results.
Familiarity with LangChain, LlamaIndex, or similar agentic frameworks.
Strong debugging, profiling, and optimization skills for AI applications.
GOOD TO HAVE JD SKILLS as below
Experience with OCR libraries like Tesseract or Azure Form Recognizer.
CV Checklist as below :-
1. Core Programming Skills
☐ Strong proficiency in Python (mention of libraries like NumPy, Pandas, FastAPI, etc.)
☐ Experience with object-oriented programming, data structures, and algorithms
2. Large Language Models (LLMs)
☐ Hands-on experience with OpenAI, Hugging Face Transformers, LLaMA, Mistral, etc.
☐ Fine-tuning or prompt-tuning of LLMs
☐ Knowledge of tokenization, attention mechanisms, and model architecture
3. Prompt Engineering
☐ Experience designing and optimizing prompts for LLMs
☐ Familiarity with few-shot, zero-shot, and chain-of-thought prompting
☐ Use of tools like PromptLayer, LangSmith, or custom evaluation frameworks
4. Vector Databases
☐ Experience with Pinecone, Weaviate, FAISS, Milvus, Qdrant, etc.
☐ Understanding of embedding generation, similarity search, and indexing
☐ Integration with LLMs for retrieval tasks
5. RAG (Retrieval-Augmented Generation) Architecture
☐ Implementation of RAG pipelines using LLMs and vector stores
☐ Experience with document chunking, embedding, and retrieval logic
☐ Tools: LangChain, Haystack, LlamaIndex
6. Agentic Libraries
☐ Experience with LangChain Agents, LangGraph workflows, or AutoGen agents
☐ Building multi-step reasoning agents or task-specific agents
☐ Integration with tools/APIs for autonomous decision-making
7. Computer Vision
☐ Experience with OpenCV, YOLO, Detectron2, MediaPipe, or PyTorch/TensorFlow CV models
☐ Projects involving image classification, object detection, OCR, or segmentation
8. Document Processing
☐ Experience with PDF parsing, OCR (Tesseract, AWS Textract, Azure Form Recognizer)
☐ Structured data extraction from invoices, contracts, forms, etc.
☐ Integration with LLMs for semantic understanding of documents
9. Deployment & MLOps
☐ Experience with Docker, Kubernetes, FastAPI, Streamlit, Gradio
☐ CI/CD pipelines for ML models
☐ Monitoring and logging tools (e.g., MLflow, Weights & Biases)
10. Soft Skills & Collaboration
☐ Experience working in Agile/SCRUM teams
☐ Strong communication and documentation skills
☐ Contributions to GitHub, open-source, or research publications