AI Engineer

·         Job Title:                       AI Engineer

·         Location:                       Krakow, Poland (3 days onsite)

·         Duration:                      Contract

Job Description: 

Technical/Domain Skills

Experience

(must)

Python, LLM, Prompt engineering, Vector databases, RAG architecture, Agentic libraries(Lang chain/Lang graph/Autogen), Computer Vision, Document Processing

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