Senior GenAI Engineer - Production-Ready AI, Remote/Hybrid

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

Benefits offered by this job

Competitive salary

Comprehensive benefits

High-impact AI projects

Growth opportunities

Collaborative culture

Job summary

Harnham in the United States is seeking a Senior/Principal Applied AI Engineer to own production-grade GenAI solutions, from prototypes through scalable deployment, with clear visibility of impact on customers and internal teams.

You will design, build, and deploy GenAI apps, develop LLM-powered solutions with prompt engineering, vector databases, and Retrieval-Augmented Generations, and deliver production-ready conversational AI and agents.

Qualifications

• Advanced Python development with GenAI libraries.
• Hands-on with large language models and prompt engineering.
• Proven experience building RAG pipelines and vector databases.
• Strong SQL skills and cloud data platforms.
• Production-grade conversational AI, clear communication to varied stakeholders.

Responsibilities

• Design, build, and deploy Generative AI applications across platforms.
• Develop LLM-powered solutions using prompt engineering and vector DBs.
• Own AI chatbots/agents with production-level performance and compliance.
• Create AI agents for real-time interactions across channels.
• Deliver PoCs for document understanding, summarisation, and knowledge tools.
• Optimize model usage, prompts, and parameters for cost and reliability.
• Collaborate with product, engineering, data, and partners to align AI with priorities.

Skills

Python

GenAI / LLMs

Prompt engineering

RAG pipelines

Vector databases

SQL

Conversational AI

Communication

Cross-functional teamwork

Tools

Cloud data platforms

LLM evaluation tooling

Job description

Harnham in the United States is seeking a Senior/Principal Applied AI Engineer to own production-grade GenAI solutions, from prototypes through scalable deployment, with clear visibility of impact on customers and internal teams.

You will design, build, and deploy GenAI apps, develop LLM-powered solutions with prompt engineering, vector databases, and Retrieval-Augmented Generations, and deliver production-ready conversational AI and agents.