Senior GenAI Engineer, LLM & Agent Platform

Staffworxs; San Francisco (CA); On-site; USD 160,000 - 260,000; Full time

Job summary

Staffworxs is seeking a Generative AI Engineer to join our enterprise AI initiatives. You will design, develop, and deploy GenAI applications to solve complex enterprise problems, spanning LLM infrastructure, agent systems, and integrations with tools like Glean, Gemini Enterprise Apps, or Claude Cowork.

You will build and maintain the LLM gateway, observability capabilities, and agent workflows, while collaborating with Data Science, Product, and Engineering teams to improve developer

Qualifications

• 5+ years of professional software/DevOps/AI infrastructure experience.
• Hands-on experience with large language models in production (prompt design, tool calls, streaming).
• Familiarity with LLM orchestration and gateway tools (LiteLLM, LangChain).

Responsibilities

• Design, develop, and deploy generative AI applications for enterprise problems.
• Contribute to AI platform: LLM infra, agents, and enterprise tools like Glean or Gemini Enterprise Apps.
• Build and maintain LLM gateway with multi-provider routing, caching, and guardrails.
• Develop LLM observability: logging, cost attribution, latency tracking, anomaly detection.
• Create and iterate AI agents/workflows with multi-step tool use and human-in-the-loop.
• Integrate MCP servers to connect agents with tools and data sources (Slack, Jira, databases).
• Design evaluation frameworks for LLM apps and agents; run regression tests and report quality metrics.
• Support VectorDB ingestion pipelines and integration with the AI platform.
• Maintain IaC (Terraform), CI/CD (GitHub Actions), and AWS resources.

Skills

Python

LLM APIs

LLM orchestration

AI tooling

Tools

Terraform

GitHub Actions

AWS

LangChain

Glean / Gemini Enterprise Apps

Job description

Staffworxs is seeking a Generative AI Engineer to join our enterprise AI initiatives. You will design, develop, and deploy GenAI applications to solve complex enterprise problems, spanning LLM infrastructure, agent systems, and integrations with tools like Glean, Gemini Enterprise Apps, or Claude Cowork.

You will build and maintain the LLM gateway, observability capabilities, and agent workflows, while collaborating with Data Science, Product, and Engineering teams to improve developer