About the role
KEY RESPONSIBILITIES
• Design, develop, and deploy autonomous AI agents and multi-agent workflows to automate complex infrastructure tasks, test generation, and failure triage.
• Build, train, and implement custom Machine Learning models tailored to our testing environment (e.g., anomaly detection, predictive analytics, and test optimization).
• Architect scalable internal tools that integrate Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) into our existing engineering ecosystem.
• Connect AI agents and ML models to our core data pipelines and databases (Snowflake, MySQL) to ensure they have access to accurate, real-time data.
• Write robust, production-ready code primarily in Python, while interfacing front-end interfaces and AECG software tools.
• Establish MLOps best practices for the project and collaborate closely with the internal engineering team to ensure seamless integration and knowledge transfer.
PREFERRED EXPERIENCE
• Professional software engineering experience with a strong focus on backend systems, infrastructure, or tooling, with a proven ability to hit the ground running on new projects.
• Hands-on experience building and deploying AI agents and agentic workflows, whether custom-built or using industry frameworks (e.g., LangChain, AutoGen, or similar).
• Proven track record of building, training, and deploying ML models in production environments using PyTorch, TensorFlow, or Scikit-Learn. Deep understanding of LLM APIs (OpenAI, Anthropic, etc.), advanced prompt engineering, and building RAG pipelines.
• Expert-level proficiency in Python and strong knowledge of UNIX/Linux environments.
• Solid understanding of database architecture and data pipelines (SQL, Snowflake, or similar).
• Experience with MLOps practices, including model deployment, monitoring, and lifecycle management.
• Knowledge of compiled programming languages, with C++ experience highly valued.
• Experience building APIs to serve ML models and AI agents (e.g., FastAPI, Flask).