Fullstack Software Engineer – AI Model Testing [1 Month Contract]

Work Type: Contractor | Permanent Remote Compensation: USD 50 – 125/hour Hours: 10 to 40 hours/week (Partial PST overlap required) Experience Required: 5 – 10 Years Contract Duration: 1 Month (Extension based on performance) Notice Period: Immediate preferredNote

• This is a contract-based, fully remote role.
• Only citizens or valid work permit holders from the US, Canada, Australia, or Western Europe are eligible.
• No medical benefits or paid leave.
• Contractors must manage their own taxes and compliance.
• Payment is based on actual hours worked.

Job OverviewWe're seeking skilled Fullstack Engineers to join cutting-edge AI projects focused on enhancing the performance of Large Language Models (LLMs) in real-world software tasks. Your work will help train, test, and validate LLMs by evaluating AI-generated code, contributing to agent-based applications, and collaborating with a high-performance team of engineers and researchers.You will play a key role in building datasets, testing model responses, and pushing AI systems closer to real developer productivity.Key Responsibilities

• Contribute to LLM-focused projects that evaluate AI performance on realistic software engineering tasks
• Build and lead agent use cases such as coding copilots, creative tools, or automation bots
• Review and rank 3–4 AI-generated code solutions per task using a structured framework
• Analyze code diffs for accuracy, efficiency, and readability
• Construct fullstack tools for data pipeline support and internal testing environments
• Identify and report edge cases in model outputs, providing well-structured rationale
• Work closely with researchers and engineers to improve model behavior and code quality

Must-Have Skills

• 5+ years of hands-on software engineering experience, including strong fullstack development
• 1+ years full-time (FTE only) at a top 50 tech company if US-based, 2+ years if located outside the US
• Deep knowledge of software design, code review, debugging, and scalable systems
• Proven expertise in building production-grade applications using modern frameworks
• Excellent communication skills for writing clear evaluation rationales
• Proficient in Git workflows, JavaScript/Python, and cloud platforms (AWS, GCP, etc.)