Senior AI/ML Full-Stack Engineer: Build LLM Apps

Horizontal Talent

Rochester (MN)

On-site

USD 70,000 - 123,000

Full time

2 days ago

Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Horizontal Talent is seeking a Senior AI/ML Full Stack Engineer to design, build, and deploy production-grade AI/ML and Generative AI solutions. This role blends hands-on AI/ML engineering with full-stack app development, cloud-native deployment, and MLOps practices.

You will work on end-to-end AI-enabled applications using LLMs, semantic search, document intelligence, and modern user interfaces, collaborating with product and security teams to deliver scalable enterprise solutions.

Qualifications

Strong hands-on development experience with Python and SQL.
Proven experience building and deploying production-grade Generative AI and LLM applications.
Experience with LLMs, prompt engineering, embeddings, semantic search, query expansion, and citation generation.
Experience developing, evaluating, deploying, and monitoring ML/NLP models.
Understanding of LLM evaluation techniques including relevance, faithfulness, hallucination reduction, and citation accuracy.
Experience implementing AI safety guardrails and Responsible AI controls.
Strong full-stack development experience, including modern front-end frameworks, backend development, REST APIs, authentication, and application integrations.
Experience building CI/CD pipelines with Azure DevOps.
Strong knowledge of Git, automated testing, build/deployment pipelines, release management, and environment configuration.
Experience with at least one major cloud platform: Azure, GCP, AWS, or OCI.
Experience with containerized application development and deployment using Docker.
Experience designing and integrating APIs and AI/ML services into enterprise applications.
Experience with production monitoring, logging, observability, troubleshooting, and application/model performance tracking.
Strong understanding of secure software development, data privacy, and enterprise application development practices.
Strong communication and cross-functional collaboration skills.

Responsibilities

Design, develop, evaluate, and deploy production-grade Generative AI, LLM, and machine learning applications.
Build LLM-powered assistants, document intelligence solutions, semantic search capabilities, embedding pipelines, and AI-enabled enterprise applications.
Develop document ingestion, processing, chunking, retrieval, and data integration workflows.
Implement prompt engineering, query expansion, citation generation, and retrieval-augmented AI capabilities.
Develop evaluation frameworks measuring answer relevance, context relevance, faithfulness, hallucination reduction, and citation accuracy.
Implement AI safety and Responsible AI controls, including guardrails, content moderation, blocked topics, and escalation logic.
Build responsive front-end applications, backend services, RESTful APIs, authentication/authorization, and integrations with AI/ML services.
Design and maintain CI/CD pipelines using Azure DevOps for automated builds, testing, security validation, and deployment.
Implement automated unit and integration testing, environment configuration, branching strategies, release management, and deployment automation.
Containerize and deploy applications using Docker and cloud-native technologies.
Establish production monitoring, logging, observability, performance tracking, and troubleshooting for AI models and applications.
Apply strong software engineering and MLOps practices including modular architecture, reusable components, version control, code reviews, testing, security, and performance optimization.
Collaborate with product owners, business stakeholders, architects, DevOps engineers, security teams, and other technical teams throughout the development lifecycle.
Translate business requirements into secure, scalable, measurable, and maintainable technical solutions.