Applied AI Engineer
UNIS · Not specified · onsite · Posted 60d ago
Not disclosedFresherfulltimeSourced from
About a minute. You'll make an account on the way through.
About this role
Overview
Item.com is seeking an Applied AI Engineer to build production AI applications that solve concrete business problems. You will combine software engineering, LLM/ML application design, data integration, evaluation, and production operations.
Responsibilities
Item.com is seeking an Applied AI Engineer to build production AI applications that solve concrete business problems. You will combine software engineering, LLM/ML application design, data integration, evaluation, and production operations.
Responsibilities
- Ship AI applications that deliver measurable operational or customer value.
- Establish repeatable approaches for evaluation, deployment, monitoring, and improvement.
- Help move AI work from prototype to maintainable product capability.
- Design and implement AI application services using Python and/or TypeScript.
- Build retrieval, classification, extraction, summarization, and decision-support capabilities as appropriate.
- Strong software engineering experience with production services, APIs, testing, and cloud deployment.
- Practical experience shipping LLM/ML-enabled applications, not only experimenting with models.
- Experience with retrieval, embeddings, vector/data stores, prompt/version management, or model evaluation is valuable.
- Ability to explain data quality, model/application tradeoffs, fallback behavior, and production incidents.
- Clear ownership mindset and ability to work from ambiguous problems to operating software.
- Develop data pipelines, APIs, storage patterns, test coverage, and deployment workflows.
- Define and run evaluations for quality, safety, latency, and cost; use findings to improve systems.
- Instrument services with logging, tracing, metrics, alerting, and production runbooks.
- Collaborate with product, operations, and platform teams on requirements, security, and lifecycle ownership.
Sourced from foundit
Skills
storage patternsCloud Deploymentmodel evaluationMetricsapisalertingloggingtracingEmbeddingsLarge Language Models (LLMs)retrievaldeployment workflowstest coveragePythonTypescriptvector data storesData PipelineMachine Learningprompt version management