Prompt Engineer

Summary

Join Halo, an international interactive media agency, as a Prompt Engineer. The ideal candidate will have experience optimizing prompts for RAG-based applications, particularly with 4.o. Key responsibilities include designing, developing, and refining prompts to improve AI outputs, conducting experiments to evaluate effectiveness, and analyzing user feedback. Proficiency in Python and experience with LangChain or similar libraries are required. The role is 100% remote with a salary in USD and involves working on challenging projects for U.S. clients.

Requirements

• Proficiency working with 4.o in RAG applications
• Excellent analytical and problem-solving abilities
• Strong communication skills to convey complex concepts clearly
• Python
• Familiarity with LangChain, LlamaIndex, or similar libraries
• Experience with async I/O (for parallel prompt testing or streaming responses)
• SQL
• RAG Frameworks - LangChain, LlamaIndex, Haystack
• LLM APIs - OpenAI GPT-4o, Azure OpenAI API, Anthropic Claude API
• Vector Databases - Pinecone, Weaviate, FAISS, Chroma, Milvus
• Embeddings - OpenAI Embeddings, SentenceTransformers (HuggingFace)
• Data Stores / DBs - PostgreSQL, MongoDB, Redis (for caching context/state)
• Evaluation & Experimentation - Prompt injection testing, prompt tuning, cost evaluation, latency analysis
• API Integration - Prompt injection testing, prompt tuning, cost evaluation, latency analysis
• UX/Data-Driven Prompting - Understanding of user intent analysis, heatmaps, feedback loops for prompt refinement
• CI/CD & Tooling - Git, GitHub Actions, Docker (for deploying prompt pipelines or microservices)
• Software Engineering Concepts - Modularity, version control, testing (unit & integration), observability/logging practices

Responsibilities

• Design, develop, and refine prompts to improve the quality and relevance of AI outputs
• Conduct experiments to evaluate prompt effectiveness and iterate based on results
• Analyze user interactions and feedback to inform prompt adjustments and enhancements
• Building and managing prompt workflows and pipelines
• Working with OpenAI SDK (e.g., openai.ChatCompletion.create())
• Data parsing and transformation for building context windows
• Writing evaluation scripts for prompt performance (A/B testing, token cost analysis)
• Frontend experimentation or tooling for UX-related prompt testing
• API integration for frontend-driven RAG queries
• Writing queries to extract structured user data or feedback logs

Preferred Qualifications

• JavaScript/TypeScript (if used)
• Using frameworks like Next.js or React (if applicable to the product’s delivery mechanism)
• Possibly used in hybrid RAG systems combining structured (DB) + unstructured sources

Benefits

• 100% RemoteWork
• Salary in USD
• Get to work on challenging projects for the U.S