Prompt Engineer - Multiple Openings

About the Role

We are seeking a Prompt Engineer to design, test, and optimize interactions with large language models (LLMs) and generative AI systems. This role sits at the intersection of AI research, product development, and user experience, helping our teams unlock the full potential of generative AI to drive business value and innovation.

Key Responsibilities

• Prompt Design & Optimization: Develop, refine, and test prompts to achieve accurate, reliable, and context-aware outputs from LLMs (e.g., GPT-4/5, Claude, LLaMA, etc.).
• Model Evaluation: Conduct experiments to evaluate prompt effectiveness, measure output quality, and track performance against benchmarks (accuracy, efficiency, consistency).
• Knowledge Engineering: Build reusable prompt libraries, templates, and frameworks tailored to business workflows and domain-specific use cases.
• Cross-Functional Collaboration: Partner with product managers, data scientists, engineers, and designers to integrate LLM capabilities into products and services.
• Documentation & Best Practices: Establish guidelines for prompt engineering, including style, structure, safety, and ethical use.
• AI Governance: Work with legal, compliance, and security teams to ensure responsible use of AI and alignment with company policies.
• Continuous Improvement: Stay current with advances in generative AI, fine-tuning techniques, and evaluation methodologies.

Qualifications

Required Skills & Experience

• Strong background in natural language processing (NLP), linguistics, or applied machine learning.
• Proficiency in Python, JavaScript, or another programming language for working with APIs and automation.
• Experience with LLM APIs (e.g., OpenAI, Anthropic, Cohere, Hugging Face).
• Demonstrated ability to design effective prompts and evaluate AI-generated responses.
• Analytical mindset with the ability to define metrics and assess performance of AI outputs.
• Excellent communication skills to translate technical findings into actionable insights.

Preferred Skills

• Experience with fine-tuning or training large language models.
• Familiarity with vector databases, retrieval-augmented generation (RAG), and knowledge grounding.
• Understanding of human-computer interaction (HCI) and conversational UX design.
• Prior experience in a domain-specific industry (finance, healthcare, legal, etc.) where prompt engineering can create business value.
• Core Technical Skills for Prompt Engineers

1. Programming & Scripting

• Python Most common for AI/ML workflows, prototyping, and API usage.
• JavaScript/TypeScript Useful for integrating prompts into web apps/products.
• Ability to write reusable code to test, iterate, and automate prompt experiments.

1. LLM APIs & Frameworks

• Experience with OpenAI API, Anthropic, Cohere, Hugging Face Transformers, LangChain, LlamaIndex, etc.
• Familiarity with tokenization, context windows, embeddings, and fine-tuning vs. prompting.

1. Data Engineering Basics

• Vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus) for retrieval-augmented generation (RAG).
• Understanding of structured/unstructured data and how to ground prompts in reliable context.

1. NLP & Linguistics

• Knowledge of natural language processing fundamentals (tokenization, sentiment, entity extraction).
• Ability to analyze model outputs for bias, coherence, and logical consistency.

1. Evaluation & Metrics

• Skills in A/B testing, benchmarking, and prompt evaluation frameworks (e.g., BLEU, ROUGE, perplexity, or custom quality metrics).
• Familiarity with human feedback pipelines (RLHF-style evaluations).

1. ML/AI Foundations

• Understanding of how LLMs work under the hood (transformers, embeddings, attention mechanisms).
• Awareness of fine-tuning, LoRA, and model adaptation techniques.
• Knowledge of AI safety, fairness, and bias mitigation.

1. Tooling & Workflow Automation

• Prompt chaining & orchestration tools (LangChain, Semantic Kernel).
• MLOps basics versioning prompts, tracking experiments (Weights & Biases, MLflow).
• Scripting experiments for efficiency (Jupyter, Colab, Git workflows).

1. Cloud & Deployment

• Working knowledge of cloud AI services (AWS Sagemaker, Azure OpenAI, Google Vertex AI).
• Experience integrating LLM workflows into production systems (REST APIs, microservices, serverless functions).

Key Attributes

• Curiosity and creativity in experimenting with language and logic.
• Detail-oriented problem solver with a growth mindset.
• Passion for building safe, ethical, and user-centric AI solutions.