AI Engineer - LLMs & Autonomous Agent Architect

Applied Medical Corporation; Rancho Santa Margarita (CA); On-site; USD 80,000 - 140,000; Full time

Benefits offered by this job

Competitive compensation

Comprehensive benefits

Education reimbursement

401(k) with match

Generous vacation

Job summary

Applied Medical Corporation seeks an AI Engineer to design and deploy advanced LLM-powered applications and autonomous agents. You will build MCP-based architectures for persistent context, orchestrate tools, and integrate with APIs and databases, working on-site in California with cross-functional teams.

You will implement RAG pipelines, vector stores, and prompt strategies, while ensuring governance, safety, and privacy. Strong Python and ML framework experience is required.

Qualifications

• Bachelor’s or Master’s in Computer Science, AI/ML, or related field (Ph.D. preferred).
• 2+ years building and deploying AI applications with LLMs (OpenAI, Anthropic, HuggingFace).
• Strong Python skills, with experience in Git, FastAPI/Flask, and ML frameworks (PyTorch, TensorFlow).
• Hands-on experience with agent frameworks (AutoGen, LangGraph, CrewAI) and orchestration strategies.
• Proficiency in vector databases (Pinecone, Milvus, ChromaDB, FAISS) and embedding techniques.
• Solid understanding of prompt engineering, RAG, and LLM optimization.
• Familiarity with cloud/on-prem deployment and containerization (Docker, Kubernetes).
• Experience implementing Model Context Protocols for context management and interoperability.
• Experience with multi-agent systems, planning algorithms, or reinforcement learning with LLMs.
• Knowledge of production-grade AI monitoring, logging, and observability.
• Excellent problem-solving skills and ability to thrive in fast-paced, collaborative environments.

Responsibilities

• LLM Application Development: Design, fine-tune, and deploy LLM-based applications for reasoning, planning, retrieval, and automation.
• Agent Systems: Build autonomous AI agents that interact with APIs, databases, and tools using frameworks like LangChain, LangGraph, AutoGen, or custom solutions.
• Context & Memory Management: Implement Model Context Protocols (MCP) for persistent context, robust coordination between agents, and seamless tool usage.
• Data & RAG Pipelines: Develop RAG pipelines, vector databases, and prompt-engineering strategies to enable context-aware responses.
• Backend & Infrastructure: Build scalable backend systems and deploy solutions on cloud or on-prem environments (Azure, AWS), with containerization (Docker, Kubernetes).
• Research & Innovation: Stay up-to-date with emerging LLM and agentic technologies and evaluate them for practical applications.
• Collaboration & Governance: Work closely with data science, product, and engineering teams while ensuring responsible AI practices, model safety, and compliance with data privacy regulations.

Skills

LLM development

Python

Git

FastAPI/Flask

ML frameworks

Agent frameworks

LangChain

LangGraph

AutoGen

CrewAI

Vector databases

Pinecone

Milvus

ChromaDB

FAISS

Embedding techniques

Docker

Kubernetes

Cloud/on-prem deployment

Model Context Protocols

Education

Bachelor’s or Master’s in CS/AI/ML

Ph.D. preferred

Tools

LangChain

LangGraph

AutoGen

CrewAI

Docker

Kubernetes

PyTorch

TensorFlow

Job description

Applied Medical Corporation seeks an AI Engineer to design and deploy advanced LLM-powered applications and autonomous agents. You will build MCP-based architectures for persistent context, orchestrate tools, and integrate with APIs and databases, working on-site in California with cross-functional teams.

You will implement RAG pipelines, vector stores, and prompt strategies, while ensuring governance, safety, and privacy. Strong Python and ML framework experience is required.