Generative AI & Prompt Engineering Specialist

Potomac Haven Inc•Washington, DC

About The Position

Our Cognitive and Generative-AI team is responsible for developing and implementing AI-driven solutions that enhance and scale AI adoption across our firm. This is a pivotal role in our AI Center for Enablement, leading the design and implementation of cutting-edge AI systems. This role leverages and adapts state-of-the-art large language models (LLMs) to solve complex business problems and identifies opportunities to build modular and reusable components. You will collaborate with our Technology Services and Business partners to build and drive solutions. You will provide delivery and ongoing support for data science, advanced analytics, and augmented intelligence technologies, executing on the strategic vision and ensuring the successful implementation of AI initiatives across the firm. Successful candidates will exhibit excellent problem-solving skills, effective communication and analytical skills, as well as strong self drive.

Requirements

About 3 years building AI-powered products or prototypes with hands-on ownership from concept to demo.
Proven track record of use of GenAI Copilot, ChatGPT, Anthropic to drive productivity initiatives across the organization with clear value metrics.
Hands-on experience building production grade AI agents using industry leading platforms.
Demonstrated excellence in prompt writing across text, image, and multimodal use cases.
Strong grasp of RAG, agentic methods, and iterative evaluation.
Hands-on experience to drive model accuracy, minimize hallucinations, and ground the model in facts, specifically when building AI agents.
Curious, adaptable, and energized by ambiguous problems and fast feedback cycles.
Empathetic collaborator who listens to stakeholders and turns needs into lovable tools.
Degree in the field of AI or similar (Computer Science, Data Science, Data Analytics, Engineering, Statistics, Mathematics or related technical field).
Prior work experience in consulting or advisory services.
You should be ready to demonstrate your skills and competency during the interview process.

Responsibilities

Provide platform, engineering, and enablement services to drive the adoption and utilization of Generative AI capabilities, fostering technological innovation and improving member experience through foundational AI capabilities.
Design, develop and deploy AI solutions with a focus on: clarify the problem, design the approach, write the prompts and prototype quickly.
Curate, process and augment high-quality multimodal data while integrating Retrieval-Augmented Generation (RAG) for robust model grounding and improved accuracy.
Implement retrieval-augmented workflows: grounding, chunking, indexing strategies, response synthesis, and guardrails for factuality and tone.
Orchestrate multi-step agents: task decomposition, tool-use design, memory and context strategies, and failure/retry logic for reliability.
Operationalize prompt systems: reusable prompt patterns, role/task separation, evaluation harnesses, and continuous refinement.
Leverage core engineering competencies in GPT algorithms, data ingestion for Large Language Models (LLMs), prompt engineering, and Natural Language Processing (NLP)/Chatbot interface construction.
Deploy solutions to a shareable environment for stakeholders.
Document decisions: assumptions, risks, test plans, and clear instructions so others can run, test, and extend your prototypes.
Communication and influence: Translate complex AI behavior into simple narratives and demos. Gather feedback from non-technical stakeholders and close the loop with measurable improvements.