Contract: Senior AI Engineer

Upwork

14 days ago

Remote, Worldwide

Senior

H1B Sponsor

Responsibilities

Design, implement, and maintain production-grade AI services for NLQ and AI agent workflows.
Evaluate NLQ system accuracy using quantitative and qualitative methods.
Build automated evaluation pipelines and regression test suites integrated into CI/CD workflows.
Design and validate ontology-driven semantic models and knowledge graphs.
Analyze NLQ failures and define structured error taxonomies for continuous improvement.
Develop and expose well-designed APIs for NLQ services and evaluation systems.
Contribute to system architecture decisions regarding scalability and reliability.
Support cloud-native deployment and operational readiness of AI services.

Strong software engineering background in building production systems using Python and APIs.
Experience evaluating NLQ or LLM-based systems, focusing on precision/recall and semantic correctness.
Hands-on expertise in designing automated test frameworks and evaluation pipelines.
Experience with cloud-native architectures, CI/CD, and production deployment of AI systems.
Knowledge of semantic modeling, ontologies, or knowledge graphs in data-driven applications.
Proven ability to design scalable and reliable systems that bridge AI models and applications.

Python