Applied AI Engineer - LLM Orchestration & Production AI

Radley James; San Francisco (CA); On-site; USD 180,000 - 275,000; Full time

Job summary

Radley James in San Francisco, CA, is hiring an ML/AI Engineer – Applied AI for an on-site, full-time role. The team builds the AI systems behind the platform, including LLM orchestration, retrieval, and evaluations, with a focus on reliability and scalable performance.

We seek 4–6+ years in production software/ML, strong Python, and hands-on experience with LLM APIs. Knowledge of RAG, embeddings, evals, and agent workflows is highly valued, along with an ability to turn complex problems into

Qualifications

• 4–6+ years building production software, ML, or applied AI systems.
• Strong Python and hands‑on experience with LLM APIs.
• Experience with RAG, embeddings, evals, structured outputs, or agent workflows.
• Strong understanding of AI quality, reliability, latency, and cost.
• Ability to turn ambiguous problems into measurable, production‑ready solutions.

Responsibilities

• Build the AI systems behind the platform—from LLM orchestration to evaluations and production reliability.
• Collaborate with engineering and product teams to shape AI features and production readiness.

Skills

Python

LLM APIs

RAG

Embeddings

Evaluations

Agent workflows

AI reliability

Tools

Go

Job description

Radley James in San Francisco, CA, is hiring an ML/AI Engineer – Applied AI for an on-site, full-time role. The team builds the AI systems behind the platform, including LLM orchestration, retrieval, and evaluations, with a focus on reliability and scalable performance.

We seek 4–6+ years in production software/ML, strong Python, and hands-on experience with LLM APIs. Knowledge of RAG, embeddings, evals, and agent workflows is highly valued, along with an ability to turn complex problems into