Senior Prompt Engineer - 100% Remote

About Us

At Hyly.AI, we’re building the first AI + Data fabric for the multifamily industry, changing the way our clients manage and improve their marketing and operations. As the intellectual capital of the industry shifts toward a blend of workforce, AI, and data, we’re proud to be at the forefront of this transformation. You'll be helping us lead this transformation!

Role Summary

Senior Prompt Engineer (100% Remote)

You will collaborate closely with product managers, ML engineers, and data scientists to design, test, and refine prompt architectures, evaluation frameworks, and multi-intent orchestration flows. The ideal candidate has deep expertise in LLMs (e.g., GPT-4, LLaMA, Mistral, DeepSeek), RAG pipelines, and prompt engineering best practices, and is passionate about building reliable and explainable AI systems. This role offers the opportunity to shape the core intelligence layer that differentiates Hyly.AI in a highly competitive market.

Key Responsibilities

• Design, build, and manage a

  centralized Prompt Library & Evaluation Store

  to ensure consistent, versioned, and reusable prompts across Hyly.AI products.
• Collaborate with product managers, ML engineers, and data scientists to define

  prompting strategies and taxonomies

  that scale across chat, mail, SMS, and voice.
• Develop and refine

  prompt templates

  (e.g., few-shot, chain-of-thought, multi-intent orchestration) for reliable and context-aware LLM performance.
• Integrate

  RAG pipelines and vector databases

  (e.g., Pinecone, Weaviate, FAISS) into prompting workflows to ground responses with accurate and relevant data.
• Create and maintain

  prompt evaluation workflows

  using frameworks like LangSmith, custom eval loops, or MECE benchmarking to measure quality and consistency.
• Implement

  guardrails and conditional logic

  (e.g., toggles, fallback handling, language switches) to reduce hallucinations and improve reliability.
• Launch

  observability dashboards and automated test cases

  to monitor prompt accuracy, latency, and success rates in real time.
• Work with cross-functional teams to

  continuously improve prompt effectiveness

  , ensuring business goals translate into scalable prompting solutions.

Must-Have Qualifications:

• Bachelor’s degree in Computer Science, Linguistics, Cognitive Science, or a related field or equivalent practical experience.
• 2+ years of hands-on experience engineering prompts for frontier Large Language Models (LLMs) such as OpenAI GPT, LLaMA, Claude, Mistral, or similar.
• Proven expertise in designing, testing, and refining prompts to optimize accuracy, reliability, and contextual alignment across diverse use cases.
• Strong experience with Retrieval-Augmented Generation (RAG) pipelines and context-injection techniques to ground LLM outputs.
• Familiarity with evaluation frameworks for LLMs (e.g., LangSmith, custom eval loops, MECE frameworks) and ability to measure/benchmark prompt performance.
• Proficiency in Python for automating prompt testing, building evaluation scripts, and integrating prompts into production workflows.
• Ability to work with vector databases (e.g., Pinecone, Weaviate, FAISS) to support semantic search and prompt-driven retrieval.
• Excellent analytical and communication skills to translate business problems into effective LLM prompting strategies.

Preferred (Nice-to-Have) Qualifications:

1. Remote Team Management Experience:

   Experience managing teams in a remote environment, ensuring effective communication and productivity.

2. Cross-Functional Team Leadership:

   Proven ability to lead cross-functional teams, managing dependencies and ensuring smooth coordination.
3. Strong collaborative development skills using Git and version control systems.