Senior AI Engineer: End-to-End LLM Apps, RAG & Agents

Robotic Technologies Automation; San Diego (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Robotic Technologies Automation in San Diego, CA seeks a hands-on Senior AI Engineer to design, build, test, and deliver enterprise-grade AI applications from concept to production-ready software. You will combine full-stack engineering with deep expertise in Generative AI, LLMs, RAG, AI agents, embeddings, and vector search.

Responsibilities include building AI-powered applications, scalable APIs and microservices, implementing testing, and deploying with Harness CI/CD.

Qualifications

• Hands-on experience with AI frameworks such as LangChain, LangGraph, LlamaIndex.
• Strong understanding of LLMs, RAG, agentic AI, prompt/context engineering and model integration.
• Experience with OpenAI, Azure OpenAI, Anthropic, Gemini, AWS Bedrock or comparable model platforms.

Responsibilities

• Independently architect and build end-to-end AI-powered applications, including UI, backend, APIs, data and AI layers.
• Develop solutions using LLMs, Generative AI, RAG, AI agents, embeddings and vector search.
• Build agentic workflows integrating enterprise applications, APIs, tools and data sources.
• Develop scalable APIs, microservices and cloud-native applications.
• Implement automated unit, integration and AI application testing.
• Use AI coding tools such as GitHub Copilot, Claude Code, Cursor, Codex or equivalent to accelerate engineering.
• Build and maintain CI pipelines and application services using Harness.
• Work closely with platform engineering to ensure applications are secure, observable and production-ready.

Skills

LLMs

RAG

Agentic AI

Prompt engineering

Model integration

API & microservices

CI/CD pipelines

Docker & Kubernetes

Tools

LangChain

LangGraph

LlamaIndex

Semantic Kernel

OpenAI / Azure OpenAI

AWS Bedrock

Harness CI/CD

GitHub Copilot

Job description

Robotic Technologies Automation in San Diego, CA seeks a hands-on Senior AI Engineer to design, build, test, and deliver enterprise-grade AI applications from concept to production-ready software. You will combine full-stack engineering with deep expertise in Generative AI, LLMs, RAG, AI agents, embeddings, and vector search.

Responsibilities include building AI-powered applications, scalable APIs and microservices, implementing testing, and deploying with Harness CI/CD.