AI Agent Orchestration Engineer - Python, LLMs, Onsite Austin

Managed Staffing, Inc.; Austin (TX); Presencial; USD 120.000 - 160.000; Tempo integral

Resumo da vaga

Managed Staffing, Inc. is hiring an AI Engineer to design, build, and operate agentic AI systems that reason over enterprise data, call tools, and execute multi‑step workflows end to end.

You will ship production services and own components from prototype through production in a hands‑on role. The role emphasizes strong Python and ML foundations, experience with LLM orchestration, and shipping LLM or GenAI applications.

Qualificações

• 3–5 years of software, ML, or data engineering experience.
• At least 1 year building LLM-based applications.
• Strong Python production coding, testing, and API development.
• Experience with LLM orchestration frameworks.
• Experience building RAG systems with embeddings and vector stores.
• Command of SQL and cloud data platforms.
• Docker + CI/CD deployment in a major cloud.

Responsabilidades

• Design and ship LLM-powered agents for multi-step tasks.
• Build and deploy multi-agent workflows with planner/executor/reviewer roles.
• Expose tools to agents via function-calling and MCP servers.
• Operationalize Retrieval-Augmented Generation pipelines (RAG).
• Integrate enterprise sources (SharePoint, Confluence, Jira, REST APIs, SQL) into agent context.
• Improve grounding and reduce hallucinations through retrieval and prompt design.
• Develop production Python services and APIs using FastAPI and Docker.
• Instrument tracing, cost accounting, latency monitoring, and logging in production.

Conhecimentos

Python

Production code

LLM orchestration

RAG systems

SQL

CI/CD

Ferramentas

LangChain

LangGraph

LlamaIndex

Semantic Kernel

PyTorch

Docker

Azure

Descrição da vaga

Managed Staffing, Inc. is hiring an AI Engineer to design, build, and operate agentic AI systems that reason over enterprise data, call tools, and execute multi‑step workflows end to end.

You will ship production services and own components from prototype through production in a hands‑on role. The role emphasizes strong Python and ML foundations, experience with LLM orchestration, and shipping LLM or GenAI applications.