AI Development Engineer
Role: AI Development Engineer
Location: Dallas, TX
Type: Contract Position
Job Description
We are seeking a highly skilled AI Development Engineer with strong expertise in telecom domains (4G/5G and OSS/BSS) and advanced AI technologies. The candidate will design and implement AI-driven solutions for test automation, leveraging LLMs and Retrieval-Augmented Generation (RAG) to enhance efficiency and accuracy in telecom testing environments.
Education and Experience:
- Bachelor s degree in computer science, Information Technology, AI/ML, Data Science, or related field.
- Certifications in AI/ML technologies , LLM development , or telecom protocols are a plus.
Key Responsibilities:
- Develop and integrate AI models for telecom test automation using Python , LLMs , and RAG techniques.
- Short-train and fine-tune AI engines with existing Verizon test scripts, scenarios, and domain-specific data.
- Generate Robot Framework scripts using GenAI to automate test case creation and execution.
- Integrate AI solutions with existing test platforms and tools for seamless automation workflows.
- Perform test execution and IrisView log analysis, generating summaries and actionable insights using AI-driven approaches.
- Collaborate with QA, DevOps, and network engineering teams to embed AI capabilities into CI/CD pipelines.
- Design and implement data pipelines for training and inference, ensuring data quality and compliance.
Required Skills:
- 3+years of experience in AI development and telecom domains (4G/5G and OSS/BSS).
- Strong proficiency in Python and AI frameworks (TensorFlow, PyTorch, Hugging Face).
- Hands-on experience with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG).
- Familiarity with GenAI-based script generation and automation frameworks like Robot Framework.
- Solid understanding of telecom protocols (LTE, 5G NR, Diameter, SIP, etc.).
- Experience in log analysis and summarization using AI/NLP techniques.
- Strong problem-solving and debugging skills for AI-driven automation solutions.
- Knowledge of MLOps practices and deployment of AI models in production.
- Experience with vector databases (e.g., Pinecone, Weaviate) for RAG implementations.
- Familiarity with API development and integration for AI services.
- Exposure to cloud platforms (AWS, Azure, Google Cloud Platform) for AI model hosting.
- Understanding of CI/CD pipelines and integration with AI workflows.
- Knowledge of data preprocessing, feature engineering, and prompt engineering for LLMs.