We are a fast-growing technology company leveraging large language models and AI to power next-generation applications. Our teams deliver high-impact solutions across diverse domains while maintaining a culture of curiosity, collaboration, and continuous learning.

We’re seeking a skilled Prompt / AI Engineer to design, implement, and optimize natural-language prompts, chains, and retrieval-augmented workflows. You’ll partner with engineering, product, and data science teams to ensure seamless integration of LLM capabilities into our services.

What You'll Do At CYBLE

• Prompt Design & Optimization
• Craft and iterate prompt templates for a variety of use cases (summarization, classification, Q&A)
• Implement few-shot examples, chain-of-thought techniques, and dynamic parameterization
• Benchmark, profile, and refine prompts to balance accuracy, latency, and cost
• Workflow & Chain Development
• Build multi-step LLM pipelines using frameworks like LangChain, LlamaIndex, or equivalent
• Integrate retrieval-augmented generation (RAG) with vector stores and document loaders
• Develop agentic workflows that orchestrate API calls, data enrichment, and user interactions
• Model Integration & Testing
• Integrate with public and private LLM services (e.g., OpenAI, Anthropic, self-hosted models)
• Automate performance tests, error-handling routines, and hallucination checks
• Monitor usage metrics, implement rate-limits, and optimize token budgets
• Collaboration & Documentation
• Work closely with backend/frontend engineers to expose LLM endpoints
• Create and maintain a prompt library, testing suite, and best-practice guidelines
• Conduct reviews, knowledge transfers, and training sessions on prompt engineering
  
  

What You’ll Need

• 3+ years of experience in AI/ML, NLP, or software engineering with a focus on prompt or LLM integration
• Strong proficiency in Python and familiarity with LLM client libraries
• Hands-on with at least one orchestration framework (LangChain, LlamaIndex, Dify, etc.)
• Experience working with vector databases (Pinecone, Weaviate, Qdrant) or embedding services
• Solid understanding of prompt-engineering techniques, chain-of-thought, and RAG concepts
• Ability to benchmark, profile, and optimize model calls for performance and cost
• Excellent written communication for clear documentation and prompt examples
  
  

Preferred (Nice-to-Have)

• Experience fine-tuning or prompt-tuning domain-specific models
• Familiarity with self-hosted LLM deployments (Hugging Face, OpenAI local runtimes)
• Background in automated evaluation metrics (ROUGE, BLEU, custom tests)
• Contributions to open-source prompt libraries or agent frameworks
• Exposure to CI/CD for AI services and observability tools
  
  

What We Offer

• Impactful Projects: Shape core LLM-driven capabilities across diverse applications
• Innovative Environment: Work with cutting-edge models, RAG pipelines, and agent frameworks
• Growth & Learning: Access to mentorship, training budgets, and conference support
  
  

Apply now to help us define the future of AI-driven applications through expert prompt engineering!

If you like working in an inclusive environment, you want to advance your career quickly, and your opinion is valued, look no further than Cyble, Inc. We are young, hungry, and ready to impact the cyber security landscape!

Cyble, Inc. takes into consideration an individual’s skillset, experience and location in making final salary determination.

All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, protected Veteran status age, or genetics, or any other characteristic protected by law.