AI Prompt Engineer
First seen by Alion on Nov 2, 2026.
Role Type: Part-Time
Time Commitment: Min of 20 hours per week - Full time (optional)
Attendance: Weekly team meetings; Quarterly Townhalls; Availability for scheduled meetings during agreed working hours
Working Schedule: Monday -Friday
Duration: 3 - 6 months
Reporting to: CEO, Solution Architect
Start date: Early November 2026
Location: Central Singapore (Hybrid – flexible combination of in-person and remote work)
Tools: Python, GitHub, AWS, LLMs
Perks & Allowances: $900 SDG monthly
Overview
Hivve is a global impact reporting company working with universities, foundations, and purpose-led organisations across eight countries. We are on a mission to transform how organisations capture and communicate their impact, using AI tools and our proprietary data models to make impact reporting simpler, smarter, and more meaningful.
About the RoleThis is a hands-on AI Prompt Engineer Internship for a minimum 3 months, with the option to extend. You will work at the intersection of product, engineering, and applied AI, helping to design, test, and refine how large language models are used within a SaaS platform. The role begins with structured prompt development and evaluation in controlled environments, and may extend into direct exposure to live production systems where AI outputs are actively used by real users. You will gain experience across the full lifecycle of AI systems—from early experimentation through to production monitoring—while working closely with engineers, product teams, and domain experts.Key ResponsibilitiesTranslate user, client, and internal requirements into structured prompts and clearly defined output specifications
Design, test, and iterate prompts to improve accuracy, consistency, and usability across core workflows
Support Alpha and Beta testing phases through structured experimentation and systematic identification of failure modes
Evaluate AI outputs using defined criteria including accuracy, reliability, edge cases, and hallucination risk
Collect, synthesise, and apply feedback from users and stakeholders to improve prompt and model performance
Test prompts across staging and production-like environments, and (in extension phase) monitor performance in live production systems
Work with multiple concurrent AI outputs and use cases, ensuring consistency and quality across different workflows
Contribute to the development of evaluation frameworks, monitoring approaches, and quality benchmarks for production systems
Assist in the development and refinement of AI agent workflows, including prompt chaining, tool use, and orchestration
Collaborate with engineers and product teams to understand system constraints, production behaviour, and deployment requirements
Document prompt iterations, production learnings, and best practices to support scalability and knowledge sharing.
Supervision and Support
Weekly in person check-ins with the CEO and senior development team with virtual collaboration with the Architect.
Clear task briefs and achievable milestones each week.
Exposure to international projects at the intersection of AI and social impact.
Students or recent graduates in Computer Science, Artificial Intelligence, Data Science, or a related technical field
Strong interest in AI, large language models, and how generative AI is applied in real-world SaaS products
Familiarity with Python, basic database concepts, and core AI/ML principles (e.g. training data, evaluation, model behaviour)
Strong analytical and problem-solving skills, with the ability to structure ambiguous problems into testable approaches
Curiosity and experimentation mindset, particularly in understanding how prompts influence model outputs and system behaviour
Interest in applying AI for social and environmental impact, and building technology that delivers measurable value
Comfortable working in cross-functional teams, including product, engineering, and domain experts
Clear written communication skills, particularly in documenting experiments, outputs, and insights
A self-starter who is proactive, enjoys learning quickly, and can operate independently in a fast-moving environment
Willingness to work flexibly, including later afternoon or evening hours where needed, to coordinate across global time zones
Comfort working in fast-moving environments where you may be supporting multiple live AI outputs and use cases simultaneously during the extension phase
Skills
Liaising with cross functional teams, Database Implementation, Production Testing, Requirement Specification, Experimentation, Failure Modes, Quality and Performance, Measuring Technology, Model Checking, Computer Science, Generative AI Application Development and Deployment in Financial Services, AI Evaluation, Structural Testing, Engaging Stakeholders, Generative AI Prompt Engineering, Concurrent Programming, integrated workflow