Senior Prompt Engineer | AI & Data Intelligence | Remote (US-based Only)
A fast-growing data intelligence company that’s building a platform to help enterprises structure, verify, and gain real-time insights from complex data using AI.
Their technology operates at the intersection of data integrity, AI automation, and enterprise scalability, and they’re now looking to bring in a Senior Prompt Engineer to help accelerate product innovation and strengthen their core AI capabilities.
About the Role
This position sits within the company’s core AI function, working closely with product and engineering teams to design, implement, and optimize LLM-driven pipelines that power intelligent data analysis and automation.
They’re particularly focused on someone who can think strategically about how prompt design and orchestration drive accuracy, reliability, and performance at scale embedding reasoning and context-awareness into production systems rather than simply writing prompts.
Key Focus Areas
- Prompt Architecture & Optimization – Designing, refining, and versioning high-performing prompts for a range of large language models (OpenAI, Claude, Gemini, Llama, Mistral, etc.)
- RAG Pipeline Development – Building and integrating Retrieval-Augmented Generation (RAG) pipelines and connecting to vector databases such as Pinecone, FAISS, or Weaviate
- LLM Application Integration – Embedding prompt logic and LLM-based features into live data workflows and production environments
- Evaluation & Benchmarking – Experimenting, testing, and refining prompts for consistency, scalability, and precision, using frameworks for automated evaluation and A/B testing
- Cross-Functional Collaboration – Working closely with data engineers, product managers, and AI researchers to translate business goals into technical solutions deployable at scale
Ideal Profile
- 4–8 years’ experience in AI/ML, NLP, or applied data science, ideally within data-heavy or enterprise SaaS environments
- Strong Python programming skills and experience with frameworks like LangChain, LlamaIndex, or PromptLayer
- Proven experience designing and deploying prompt engineering solutions in production, particularly for enterprise or regulated industries
- Understanding of LLMOps concepts such as observability, evaluation, and fine-tuning workflows
- Excellent communication and collaboration skills across technical and non-technical teams
- Passion for AI alignment, reasoning, and building trustworthy systems that connect human insight with machine intelligence
The Opportunity
This is a high-ownership role with visibility across the entire AI stack from research and experimentation through to production deployment. The successful candidate will play a central role in shaping how AI interacts with complex, trusted data at scale, while driving measurable improvements in automation, accuracy, and insight generation.