AI Agent Engineer

BrothersTech; United States; On-site; USD 120,000 - 180,000; Full time

Job summary

BrothersTech in the United States is seeking a skilled AI engineer to design and develop agents using LLMs and agentic frameworks, building autonomous and semi-autonomous systems for business automation. You’ll implement tool calling, reasoning, planning, and task execution workflows to coordinate tasks across diverse AI agents.

You will integrate with REST APIs, databases, and external tools, develop RAG pipelines, prompts, memory management, and human-in-the-loop workflows.

Qualifications

• Bachelor's or Master's degree in Computer Science, AI, Data Science, or related field.
• Experience with Python and large language models in production.
• Experience with agent frameworks and tool integration in enterprise apps.

Responsibilities

• Design and develop AI agents using LLMs and agentic frameworks.
• Build autonomous and semi-autonomous agents for business process automation.
• Implement tool calling, function calling, reasoning, planning, and task execution workflows.
• Develop multi-agent systems that coordinate tasks across specialized AI agents.
• Integrate AI agents with REST APIs, enterprise applications, databases, and external tools.
• Build RAG pipelines using embeddings, vector databases, and enterprise knowledge sources.
• Develop prompt templates, structured outputs, memory management, and context-handling strategies.
• Implement human-in-the-loop approval workflows for sensitive actions.
• Evaluate agent accuracy, reliability, latency, and cost using appropriate testing frameworks.
• Implement safeguards against prompt injection, unauthorized tool use, and unsafe outputs.
• Deploy AI agent applications using Docker, cloud platforms, and production APIs.
• Monitor agent execution, troubleshoot failures, and optimize performance.
• Collaborate with software engineers, product managers, data scientists, and AI researchers.

Skills

Python programming

LLMs

Agent frameworks

Prompt engineering

APIs integration

RAG & embeddings

OpenAI/Anthropic

FastAPI/Flask

Git & testing

Security awareness

Education

Bachelor's or Master's in CS/AI

Tools

Docker

Kubernetes

LangSmith

Arize Phoenix

Weaviate / Pinecone / FAISS

Job description

Industry: Artificial Intelligence / Generative AI

Key Responsibilities

• Design and develop AI agents using LLMs and agentic AI frameworks.
• Build autonomous and semi-autonomous agents for business process automation.
• Implement tool calling, function calling, reasoning, planning, and task execution workflows.
• Develop multi-agent systems that coordinate tasks across specialized AI agents.
• Integrate AI agents with REST APIs, enterprise applications, databases, and external tools.
• Build RAG pipelines using embeddings, vector databases, and enterprise knowledge sources.
• Develop prompt templates, structured outputs, memory management, and context-handling strategies.
• Implement human-in-the-loop approval workflows for sensitive or high-impact actions.
• Evaluate agent accuracy, reliability, latency, and cost using appropriate testing frameworks.
• Implement safeguards against prompt injection, unauthorized tool use, and unsafe outputs.
• Deploy AI agent applications using Docker, cloud platforms, and production APIs.
• Monitor agent execution, troubleshoot failures, and optimize performance.
• Collaborate with software engineers, product managers, data scientists, and AI researchers.

Required Technical Skills

• Strong programming experience in Python.
• Hands-on experience with LLMs and generative AI applications.
• Experience with agent frameworks such as LangGraph, LangChain, CrewAI, or AutoGen.
• Knowledge of prompt engineering, tool calling, and structured output generation.
• Experience integrating REST APIs, databases, and third-party services.
• Understanding of RAG, embeddings, semantic search, and vector databases.
• Familiarity with OpenAI API, Anthropic API, or open-source language models.
• Experience with FastAPI, Flask, or similar backend frameworks.
• Knowledge of Git, testing, debugging, and software engineering best practices.
• Understanding of authentication, API security, and responsible AI development.

Preferred Qualifications

• Experience building multi-agent orchestration systems.
• Familiarity with vector databases such as Pinecone, Weaviate, Milvus, or FAISS.
• Experience with model evaluation and observability tools such as LangSmith or Arize Phoenix.
• Knowledge of AWS, Azure, or Google Cloud Platform.
• Experience with Docker, Kubernetes, and CI/CD pipelines.
• Familiarity with MCP (Model Context Protocol) and agent-to-tool integrations.
• Experience with workflow automation platforms and event-driven architectures.
• Knowledge of LLM fine-tuning, model serving, and inference optimization.
• Experience implementing agent memory, state persistence, retries, and failure recovery.

Education

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related field.
• Equivalent practical experience may be considered.