AI Engineer - Entry Level

We are looking for a Fresher/Junior AI Engineer to support the development of AI-powered applications for SAP-focused enterprise environments, with a strong focus on Retrieval-Augmented Generation, document intelligence, and LLM-based automation.
This role is not focused on traditional Machine Learning research. Instead, the main responsibility is to build practical AI solutions using Large Language Models, RAG pipelines, AI agents, document processing workflows, and backend services that support SAP-related business processes and enterprise data workflows.
You will work on systems that can understand business and SAP-related documents, retrieve relevant information, generate reliable answers, and support automation across areas such as procurement, master data, approvals, supplier management, and other enterprise operations.
Fresh graduates with strong AI/RAG-related projects are welcome. Candidates with practical experience in RAG, LLM applications, or document processing will be considered for Junior-level responsibilities.
Key Responsibilities
1. RAG and LLM Application Development
Support the design and development of AI applications focused on Retrieval-Augmented Generation using LLMs such as OpenAI, Claude, or similar models.
Build and maintain RAG pipelines covering data ingestion, parsing, chunking, embedding, retrieval, and response generation.
Apply prompt engineering techniques to improve answer quality, task execution, and response consistency.
Support the development of AI agents and workflows using frameworks such as LangChain, LlamaIndex, or similar tools.
Learn and evaluate when fine-tuning may be needed if standard RAG cannot meet domain-specific knowledge or accuracy requirements.
2. Document Processing and Data Preparation
Extract, clean, and structure data from formats such as PDF, Word, Excel, Markdown, and images.
Use document parsing tools such as Docling, Unstructured, PyMuPDF, or similar libraries.
Prepare unstructured enterprise documents for search, retrieval, and LLM processing.
Support improvements in document extraction quality, especially for complex or inconsistent business documents.
3. Chunking, Embedding, and Vector Search
Implement and test chunking strategies such as fixed-size, recursive, semantic, parent-child, and tokenizer-aware chunking.
Work with embedding models to convert documents and queries into searchable representations.
Support vector database setup and indexing to improve retrieval speed, relevance, and scalability.
Experiment with different chunking and embedding approaches to improve RAG output quality.
4. Retrieval Optimization
Improve retrieval quality using hybrid search, re-ranking, query rewriting, and metadata filtering.
Go beyond basic similarity search by testing different retrieval strategies.
Evaluate whether retrieved documents are relevant enough for LLM-generated responses.
Support continuous improvement of retrieval accuracy based on testing, user feedback, and real use cases.
5. Backend, Data, and Deployment
Develop AI services and APIs using Python, FastAPI, or similar frameworks.
Use TypeScript when needed for application integration.
Work with SQL databases and cloud or object storage services such as S3.
Support deployment, monitoring, testing, and lifecycle management of AI applications.
6. Collaboration and Product Delivery
Work with product, consulting, and engineering teams to understand business requirements and technical constraints.
Translate business needs into practical AI features for enterprise use cases.
Contribute to technical documentation, testing, and implementation planning.
Validate AI outputs to ensure accuracy, reliability, and business relevance.