SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
heu.ai is an AI-focused company building platforms and solutions to help enterprises enhance their business and tackle complex challenges. The company works closely with clients to turn business ideas into practical AI products and strategies, supporting organizations in understanding AI capabilities, defining use cases, and implementing end-to-end solutions.
The Prompt Engineer is responsible for designing, testing, and refining prompts that optimize the performance of AI models across heu.ai's products and client solutions. This full-time role is based in Kochi and involves close collaboration with AI developers, data scientists, and product teams.
Day-to-day responsibilities include:
- Creating and refining text prompts for AI-based video and image generation tools (OpenAI, Midjourney, Pika Labs, Seedance)
- Implementing evaluation harnesses, guardrails, and regression tests to ensure output quality is measurable and stable over time
- Designing, building, testing, and iterating on prompts and prompt chains for production LLM workflows across client delivery and internal automation
- Collaborating with design and marketing teams to produce creative visuals for campaigns
- Experimenting with different prompt styles, lighting, composition, and storytelling to achieve desired results
- Maintaining a prompt library for reuse and training
- Ensuring brand consistency and output quality across visuals
- Understanding project requirements, crafting prompt structures, and creating evaluation criteria
- Running experiments to improve model accuracy, reliability, and user experience
- Documenting prompt patterns and best practices
- Analyzing user interactions and iterating on prompts based on feedback and metrics
- Contributing to internal knowledge sharing and supporting client engagements by shaping prompt strategies aligned with business goals
Requirements:
- Minimum 2 years building software or AI/LLM components, including hands-on experience crafting and iterating prompts for real applications
- Working knowledge of LLM fundamentals: context windows, few-shot prompting, function/tool calling, structured outputs, and RAG basics
- Proficiency in Python (or similar) and comfort with APIs, JSON, and version control (Git)
- A test-and-measure mindset — evaluating output quality rather than relying on subjective assessment
- Clear written English and strong documentation habits
