Senior GenAI Engineer — Production AI & Chatbots

Harnham; Minnesota; Hybrid; USD 150,000 - 205,000; Full time

Benefits offered by this job

Competitive salary

Comprehensive benefits package

Career growth opportunities

Job summary

Harnham in the United States seeks a Senior/Principal Applied AI Engineer to own end-to-end GenAI solutions, from prototype to deployment, across client-facing and internal platforms.

This role emphasizes scalable, production-grade AI leveraging prompt engineering, retrieval augmentation, vector databases, and collaboration with product, engineering, and data teams to deliver measurable business value.

Qualifications

• Extensive hands-on GenAI experience in commercial settings.
• Advanced Python with GenAI libraries.
• Experience with large language models and prompt engineering.
• Experience delivering production-grade conversational AI.
• Ability to communicate complex AI concepts clearly to stakeholders.
• Comfort in fast-paced, cross-functional environments.

Responsibilities

• Design, build, and deploy Generative AI apps across client-facing and internal platforms.
• Develop LLM-powered solutions using prompt engineering, vector databases, and Retrieval-Augmented Generation pipelines.
• Build and own AI chatbots and conversational agents to production standards, including performance and compliance.
• Create AI agents across digital and voice channels for real-time interactions.
• Deliver proof-of-concept solutions for use cases like document understanding and knowledge assistants.
• Optimize model usage, prompts, and parameters for cost and reliability.
• Collaborate with product, engineering, data, and external partners to align AI with business priorities.

Skills

Python

LLMs

Prompt engineering

LLM evaluation

RAG pipelines

Vector databases

SQL

Cloud data platforms

Conversational AI

Communication

Cross-functional

Tools

Vector databases

Job description

Harnham in the United States seeks a Senior/Principal Applied AI Engineer to own end-to-end GenAI solutions, from prototype to deployment, across client-facing and internal platforms.

This role emphasizes scalable, production-grade AI leveraging prompt engineering, retrieval augmentation, vector databases, and collaboration with product, engineering, and data teams to deliver measurable business value.