Senior Prompt Engineer(A46213)

AI Rudder; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

AI Rudder is seeking a Senior Prompt Engineer to lead the design, testing, improvement, and launch of prompts, AI workflows, and LLM-powered solutions for complex business use cases across multiple countries. You will work with product, engineering, data, operations, and regional teams to turn real business needs into scalable AI capabilities that are reliable, and measurable.

Success means AI outputs that are more accurate, consistent, and safe; prompts that are tested and documented before

Qualifications

• Bachelor's degree or above.
• 2+ years hands-on experience with LLMs, prompt engineering, or GenAI applications.
• Strong skills in prompt design, context engineering, and evaluation metrics.

Responsibilities

• Design and improve system prompts, user prompts, few-shot examples, output formats, tool-use instructions, and conversation flows for LLM applications, RAG systems, and automated workflows.
• Own prompt quality from prototype to production, including version control, regression testing, AB testing, evaluation criteria, launch checklists, and ongoing improvement.
• Build and maintain evaluation frameworks that measure task success, accuracy, groundedness, hallucination rate, safety, response time, token cost, user satisfaction, and business impact.
• Adapt prompts, workflows, tone, language, compliance requirements, and business logic to fit different markets and stakeholders.
• Work with regional teams, clients, product managers, solution architects, and data engineers to clarify requirements, manage dependencies, and deliver projects on tight timelines.
• Test prompts against risks such as prompt injection, jailbreaks, conflicting instructions, sensitive data leaks, unsafe responses, compliance gaps, and model failures.
• Create reusable prompt libraries, templates, documentation, and playbooks to help teams deliver faster across countries and projects.
• Stay up to date with developments in LLMs, RAG, model evaluation, model selection, and multimodal AI, and turn new capabilities into practical business solutions.

Skills

Prompt design

Context engineering

Instruction hierarchy

Output format design

A/B testing

Model evaluation

English and Mandarin

Cross-country coordination

Education

Bachelor's degree or above

Tools

RAG systems

OpenAI / Anthropic / Google Gemini

Vector search

Testing pipelines

Job description

Work Arrangement: Onsite, Monday to Friday

About the Role

We are looking for a Senior Prompt Engineer to lead the design, testing, improvement, and launch of prompts, AI workflows, and LLM-powered solutions for complex business use cases across multiple countries. You will work closely with product, engineering, data, operations, and regional business teams to turn real business needs into AI capabilities that are reliable, scalable, and measurable.

Success in this role means AI outputs that are more accurate, consistent, and safe; prompt changes that are tested, documented, and traceable before release; shared frameworks that teams in each country can reuse and adapt to local needs; and cross-functional teams that deliver faster because requirements and risks are clearly translated into AI designs.

Responsibilities

• Design and improve system prompts, user prompts, few-shot examples, output formats, tool-use instructions, and conversation flows for LLM applications, RAG systems, and automated workflows.
• Own prompt quality from prototype to production, including version control, regression testing, A/B testing, evaluation criteria, launch checklists, and ongoing improvement.
• Build and maintain evaluation frameworks that measure task success, accuracy, groundedness, hallucination rate, safety, response time, token cost, user satisfaction, and business impact.
• Adapt prompts, workflows, tone, language, compliance requirements, and business logic to fit different markets and stakeholders.
• Work with regional teams, clients, product managers, solution architects, and data engineers to clarify requirements, manage dependencies, and deliver projects on tight timelines.
• Test prompts against risks such as prompt injection, jailbreaks, conflicting instructions, sensitive data leaks, unsafe responses, compliance gaps, and model failures.
• Create reusable prompt libraries, templates, documentation, and playbooks to help teams deliver faster across countries and projects.
• Stay up to date with developments in LLMs, RAG, model evaluation, model selection, and multimodal AI, and turn new capabilities into practical business solutions.

Minimum Qualifications

• Completion of Bachelor's Degree or above.
• 2 years of hands-on experience with LLMs, prompt engineering, RAG, AI agents, or GenAI applications.
• Strong skills in prompt design, context engineering, instruction hierarchy, and structured output design, with the ability to define evaluation metrics, build test cases, analyze model outputs and failures, and make data-driven improvements.
• Experience with production LLM systems, such as RAG, tool or function calling, agent workflows, knowledge retrieval, vector search, evaluation pipelines, or monitoring.
• Strong project coordination skills in fast-paced, high-pressure environments with multiple stakeholders.
• Excellent communication skills in English (our official working language) and Mandarin, as this role works closely with internal and external stakeholders in Greater China.
• Willing and able to travel internationally for client workshops, project delivery, user research, and regional rollouts.

Preferred Qualifications

• Experience coordinating projects across multiple countries.
• Familiarity with mainstream LLMs and platforms such as OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, or open-source models such as Llama/Qwen.

About AI Rudder

AI Rudder is a conversational AI company on a mission to transform how businesses communicate with their customers — across voice and digital channels that feel genuinely human.

Founded in 2019 and headquartered in Singapore, we're building technologies that bridge languages, enhance understanding, and enable meaningful human–machine communication at scale.

Today, we serve 500+ enterprise clients globally processing 50 million calls daily and having delivered more than 8 billion calls to date.

Most recently, we have raised $50M in a Series B fundraising from leading global investors including Tiger Global, Peak XV Partners, and Cathay Innovation.

How We Work

AI-first: AI isn't a tool we reach for. It's the default we start from. Every team, every workflow: AI-first.

Global Collaboration: We operate globally and work as one team. Distance is a logistics problem, not a cultural one. We build the habits that make distributed teams actually work.

Communication Principle: Simple, Trust, Transparent. We remove unnecessary complexity so people can focus on what matters most.

What We Offer

Learning & Development: Continuous learning through real projects, knowledge sharing session, mentorship, and cross-functional collaboration.

Performance Recognition: Regular performance reviews, feedback, and opportunities for career progression.

Global Exposure: Collaborate with international teams, global rotations, and work with global enterprise customers.

Meaningful Impact: Build AI solutions that create real value for businesses around the world.

Ownership & Autonomy: Freedom to take initiative and drive outcomes.

Team Engagement: Team Building, Local & Global Gatherings & Local Events Celebration.

AI Rudder is an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees and applicants.