Project Overview We are sourcing independent Search Engine Evaluation Specialists to provide their expertise for an AI benchmark evaluation project.
AI Development & Programmatic Reasoning Specialist - Intermediate (AI Community)
Job description
About the Role: At TELUS Digital, we are building the future of software development. As a Specialist in our Core Engineering & AI Development Community, you are the architect behind the "Code-Gen" revolution. Your mission is to push the boundaries of how Large Language Models (LLMs) understand logic, syntax, and architectural patterns. You will join an elite squad of developers tasked with training AI to solve complex algorithmic challenges, optimize legacy codebases, and master multiple programming languages. At TELUS, you aren't just writing code; you are teaching AI how to think like a Senior Engineer.
What You’ll Do (Key Responsibilities):
- Algorithmic Reasoning Validation: Audit and refine "Chain-of-Thought" (CoT) reasoning for complex coding tasks in Python, JavaScript, Java, and C++.
- Code Quality & Security Auditing: Evaluate AI-generated code for security vulnerabilities (e.g., SQL injection, buffer overflows) and adherence to clean-code principles (SOLID, DRY).
- Multi-Turn Debugging Strategy: Design and test complex multi-turn scenarios where the AI must identify, explain, and fix bugs in existing code blocks.
- NLP-to-Code Translation: Optimize the relationship between natural language prompts and functional code outputs, ensuring the AI captures subtle logic requirements.
- LLM Benchmarking: Execute and analyze performance benchmarks for coding models, identifying "logic gaps" in how the model handles specific libraries or frameworks.
You will be redirected to the company's website to complete your application.