AWISEE - AI Engineer (Data Guardrails & LLM Ingestion Pipelines)

Client: AWISEE

Location: Belgrade, 00, rs

Contract: Freelance

Job Description

This is a remote position. We are looking for a highly skilled AI Engineer to design and build robust data ingestion, cleaning, validation, and LLM enhancement pipelines that power our AI applications. You will transform raw, unstructured data into high-quality, AI-ready datasets while implementing guardrails that ensure accuracy, consistency, and reliability.

Key Responsibilities

· Design and develop scalable data ingestion pipelines for structured and unstructured data.

· Build automated data cleaning, normalization, and preprocessing workflows.

· Develop AI-powered enrichment pipelines using LLMs (OpenAI, Claude, Gemini, etc.).

· Implement data quality validation and AI guardrails.

· Develop prompt engineering workflows for data transformation.

· Build document processing pipelines for PDFs, Word documents, CSVs, websites, and APIs.

· Develop Retrieval-Augmented Generation (RAG) pipelines.

· Create evaluation frameworks for LLM quality and accuracy.

· Build ETL/ELT workflows for AI-ready datasets.

· Integrate vector databases for semantic search.

· Monitor pipeline performance, cost, latency, and data quality.

· Collaborate with cross-functional teams to deliver production AI systems.

Requirements

Required Technical Skills
Programming

• Python (Expert)
• SQL
• Git

AI & LLMs

• OpenAI API
• Anthropic Claude API
• Google Gemini API
• Prompt Engineering
• Function Calling
• Structured Outputs

AI Frameworks

• LangChain
• LlamaIndex
• DSPy (Preferred)
• PydanticAI (Nice to Have)

Data Engineering

• Pandas
• Polars
• ETL/ELT Pipelines
• Apache Airflow (Preferred)
• Data Validation Frameworks

Vector Databases

• Pinecone
• Weaviate
• Qdrant
• ChromaDB
• FAISS

Cloud & Infrastructure

• Docker
• Kubernetes (Preferred)
• AWS / Azure / GCP
• Linux

Databases

• PostgreSQL
• MongoDB
• Redis

Preferred Qualifications

· Experience building production-grade AI systems.

· Strong understanding of RAG architectures.

· Experience implementing AI guardrails and hallucination mitigation.

· Experience with OCR and document parsing.

· Experience with embedding models and semantic search.

· Knowledge of data governance and security best practices.

Success Metrics

· Build scalable ingestion pipelines.

· Deliver automated data cleaning and LLM enhancement workflows.

· Implement AI guardrails to improve output quality.

· Develop evaluation pipelines for LLM performance.

· Contribute to a production-ready AI platform.