Agentic AI Engineer

Robotics Technologies; San Jose (CA); On-site; USD 105,000 - 149,000; Part time

Job summary

Robotics Technologies in San Jose, CA is seeking an Agentic AI Engineer to build autonomous AI systems and intelligent agents that reason, plan, and complete multi-step tasks with minimal human intervention. You will connect large language models to enterprise applications, APIs, and external data sources in an onsite, contract role.

Collaborate with data scientists, software engineers, and solution architects to design reliable agent behavior for enterprise use cases.

Qualifications

• 5–8 years software/AI/machine learning experience.
• 2+ years hands-on LLM-based application development.
• Proven experience building AI agents and multi-agent systems.
• Strong Python and API integration skills.
• Experience with RAG pipelines and vector databases.
• Knowledge of cloud-based AI services and deployment.
• Understanding of AI safety and security in apps.
• Production experience moving prototypes to production.

Responsibilities

• Design and develop autonomous AI agents for enterprise apps.
• Build multi-agent workflows for complex tasks and decisions.
• Integrate LLMs with REST APIs, databases, and tools.
• Develop RAG-based apps to improve information retrieval.
• Implement agent memory, planning, and orchestration.
• Create evaluation frameworks for agent accuracy and reliability.
• Optimize prompts, latency, and token use.
• Implement monitoring and security controls for AI systems.

Skills

Python programming

LLM-based apps

AI agent development

API integration

RAG pipelines

Vector search

Cloud deployment

AI safety awareness

Education

Bachelor's degree in CS/AI/SE

Master's degree (advantage)

Certifications in cloud AI (preferred)

Tools

LangChain

LangGraph

CrewAI

AutoGen

Semantic Kernel

Job description

Robotics Technologies is seeking an Agentic AI Engineer to help build autonomous AI systems and intelligent agents designed to reason, plan, and complete multi-step tasks with minimal human intervention. In this contract role based onsite in San Jose, CA, you will create agent-based workflows that connect large language models to enterprise applications, APIs, and external data sources.

This position centers on turning agent concepts into working systems, including retrieval-augmented generation (RAG) components, agent memory and orchestration, and production-minded evaluation and monitoring. You will collaborate across data science, software engineering, and solution architecture to design reliable agent behavior for enterprise use cases.

Key Responsibilities

• Design and develop autonomous AI agents for enterprise business applications.
• Build multi-agent workflows to support complex task execution and decision-making.
• Integrate LLMs with REST APIs, databases, and external enterprise tools.
• Develop RAG-based applications to improve contextual information retrieval.
• Implement agent memory, planning, reasoning, and orchestration mechanisms.
• Create evaluation frameworks to measure agent accuracy and reliability.
• Optimize prompts, model responses, latency, and token consumption.
• Implement monitoring, logging, and security controls for AI agent systems.
• Collaborate with data scientists, software engineers, and solution architects.
• Maintain technical documentation and support production deployments.

Required Qualifications

• 5-8 years of experience in software engineering, AI, or machine learning.
• 2+ years of hands‑on experience with LLM-based application development.
• Practical experience developing AI agents and multi-agent systems.
• Strong Python programming skills and API integration experience.
• Experience implementing RAG pipelines and vector search solutions.
• Knowledge of cloud‑based AI services and deployment environments.
• Understanding of AI safety, responsible AI, and application security.
• Experience taking AI prototypes into production environments.
• Bachelor’s degree in Computer Science, Artificial Intelligence, Software Engineering, or a related technical field.
• Practical project experience with autonomous agents, LLM orchestration, and intelligent automation is highly valued.

Technologies and Tools

• Python, LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel
• LLMs including GPT, Claude, Llama
• Retrieval‑Augmented Generation (RAG), vector databases
• Prompt engineering, tool calling, function calling
• Vector databases: Pinecone, Weaviate, Chroma
• AWS Bedrock, Azure AI Foundry, Google Vertex AI
• REST APIs

Academic Qualifications and Certifications

• Bachelor’s degree in Computer Science, Artificial Intelligence, Software Engineering, or a related technical field.
• Master’s degree in Machine Learning, Computational Linguistics, or Data Science is an added advantage.
• Certifications in AWS Generative AI, Microsoft Azure AI, or Google Cloud Generative AI are preferred.

Location: San Jose, CA (onsite)
Compensation: USD 92 - 92 per hourly
Experience: 5 years
Job Type: contract