Agentic AI Engineer: LLM Orchestration & Scalable AI

Elevait Solutions LLC; Palo Alto (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

A Silicon Valley-based, publicly traded data security software company is seeking engineers to design and build agentic AI systems, tools, and automated evaluation frameworks. You will work on memory, tool orchestration, and enterprise API integrations, partnering across product, security and platform teams to productionize AI use cases.

Ideal candidates have 4+ years in software engineering, hands-on experience with LLM-powered workflows, and strong backend/API knowledge.

Qualifications

• 4+ years of professional software engineering including 1+ year building LLM-powered apps or agents.
• Hands-on experience building agentic workflows with tool calling and an LLM SDK such as OpenAI or Anthropic.
• Backend fundamentals with REST/GraphQL APIs, OAuth2/SAML/RBAC, and SQL/NoSQL databases.
• Experience with a cloud platform (AWS or GCP) including compute, storage and managed AI services.

Responsibilities

• Assess where agentic approaches outperform conventional solutions for internal workflows.
• Design and build agentic systems covering tool orchestration, agent reasoning, memory, MCP integrations, and human-in-the-loop steps.
• Build automated evals, simulation tests, and regression frameworks to keep AI systems reliable as they scale.
• Implement AI guardrails, data lineage, auditability, and responsible AI practices.
• Prototype and evaluate emerging AI tools and technologies.
• Deliver pilots, proofs of concept, and scalable implementations across engineering teams.
• Integrate agents with enterprise APIs and SQL/NoSQL databases using RBAC.
• Partner with product, security, platform, and business teams to productionize AI use cases.

Skills

Python development for LLM-powered

Agentic AI systems

Cloud-native backend & API development

Tools

Docker

Kubernetes

OpenAI API

Anthropic API

LangGraph

Job description

A Silicon Valley-based, publicly traded data security software company is seeking engineers to design and build agentic AI systems, tools, and automated evaluation frameworks. You will work on memory, tool orchestration, and enterprise API integrations, partnering across product, security and platform teams to productionize AI use cases.

Ideal candidates have 4+ years in software engineering, hands-on experience with LLM-powered workflows, and strong backend/API knowledge.