Llm Agent Jobs in Michigan (NOW HIRING)

... or LLM-based applications. 3. Proven experience designing and deploying multi-agent or multi-service architectures in production -- not just notebooks or demos. As one 2026 hiring analysis puts it ...

Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed. * Implement guardrails ...

Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed. Implement guardrails, prompt ...

Experience building evaluation and observability pipelines for LLM/agent systems -- offline eval sets, LLM-as-judge scoring, and tracing tools (LangSmith, Langfuse, OpenTelemetry, or equivalent) to ...

Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed. * Implement guardrails ...

Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed. * Implement guardrails ...

Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed. * Implement guardrails ...

Implement evaluation pipelines and observability/tracing for every agent (golden datasets, LLM-as-judge scoring, regression alerts) so quality is measurable, not assumed. * Implement guardrails ...

You'll design, implement, and operationalize LLM/agent workflows, integrate internal and external data sources, and partner with Ontology Leads to shape data for maximum automation. This is not a ...

You'll design, implement, and operationalize LLM/agent workflows, integrate internal and external data sources, and partner with Ontology Leads to shape data for maximum automation. This is not a ...

Technical fluency in modern LLM/agent stacks, MLOps, evaluation methods, and the practical limitations of current models, combined with business judgment about when not to automate. Position Type:

Technical fluency in modern LLM/agent stacks, MLOps, evaluation methods, and the practical limitations of current models, combined with business judgment about when not to automate. Position Type:

Hands-on experience with LLM-based applications, AI frameworks, or agent tooling (e.g., LangChain, Semantic Kernel, custom orchestration frameworks).* Solid understanding of Prompt engineering and ...

Deploy agent microservices and data pipelines using GCP infrastructure (Vertex AI, Cloud Run / GKE, BigQuery, Pub/Sub, CI/CD with Docker/Kubernetes). * LLM Observability & Testing: Build robust ...

Hands-on experience with LLM-based applications, AI frameworks, or agent tooling (e.g., LangChain, Semantic Kernel, custom orchestration frameworks). * Solid understanding of Prompt engineering and ...

Hands-on experience with LLM-based applications, AI frameworks, or agent tooling (e.g., LangChain, Semantic Kernel, custom orchestration frameworks). * Solid understanding of Prompt engineering and ...

... agent workflows 4. Train, fine-tune, and re-train ML models and LLMs as required, including ... including LLM evals and red-teaming) for algorithm development and test various scenarios 6. ...

Key Responsibilities • Develop and productionize LLM, RAG, and multi agent solutions using approved client patterns • Define evaluation metrics (quality, latency, cost, adoption) and publish KPI ...

The ideal candidate has shipped LLM-powered products in production, is fluent in prompt design patterns and agent architectures, and brings strong judgment about when and how to apply different LLM ...

Develop production-grade code for AI agent frameworks, backend services, frontend applications, and LLM-powered workflows. * Build AI capabilities including natural language to SQL, semantic search ...