You are viewing a preview of this job. Log in or register to view more details about this job.

Agentic AI Engineer

Neurohire.ai
Email

About NeuroHire

NeuroHire is a Texas-based AI-powered SaaS company building intelligent technology for the modern hiring ecosystem. Our platform combines Generative AI, Machine Learning, automation, and job-market data to help users discover, organize, and act on career opportunities more efficiently.

We are expanding our AI engineering team and are looking for an Agentic AI Engineer to help build intelligent AI agents capable of reasoning through tasks, using tools, interacting with APIs, retrieving information, and completing multi-step workflows.

Role Overview

As an Agentic AI Engineer, you will help design, develop, test, and improve AI agents and multi-step AI workflows for NeuroHire's products.

You will work closely with AI/ML Engineers, Software Engineers, Data Scientists, and Product teams to turn business requirements into reliable agentic systems.

This is an entry-level opportunity for candidates with hands-on experience through academic projects, internships, research, hackathons, GitHub projects, or personal AI projects.

What You'll Do

  • Design and develop AI agents capable of completing multi-step tasks.
  • Build agent workflows involving reasoning, planning, tool usage, and decision-making.
  • Develop AI-powered workflows using Large Language Models (LLMs).
  • Integrate LLMs with internal systems, APIs, databases, and external tools.
  • Build agents capable of retrieving and processing relevant information.
  • Develop Retrieval-Augmented Generation (RAG) workflows.
  • Implement function calling and structured tool use.
  • Create reusable agent prompts, instructions, tools, and workflows.
  • Experiment with different agent architectures and orchestration patterns.
  • Build workflows for information retrieval, classification, summarization, recommendation, and automation.
  • Connect AI agents with REST APIs and backend services.
  • Work with vector databases and embedding-based search.
  • Evaluate agent accuracy, reliability, latency, and cost.
  • Identify hallucinations, incorrect tool usage, and failure scenarios.
  • Create test cases and evaluation datasets for agent workflows.
  • Implement safeguards and validation mechanisms for AI-generated outputs.
  • Collaborate with software engineers to move AI prototypes into production.
  • Monitor and improve agent performance after deployment.
  • Document prompts, workflows, architectures, experiments, and results.
  • Stay current with developments in Agentic AI, LLMs, AI agents, and AI application development.

What We're Looking For

  • Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Software Engineering, Information Technology, or a related field.
  • 0–1 year of experience in AI Engineering, Machine Learning, Generative AI, Software Engineering, or a related area.
  • Strong understanding of Generative AI and Large Language Models.
  • Hands-on experience building AI-powered applications or agent workflows.
  • Strong Python programming skills.
  • Understanding of APIs, JSON, databases, and software development fundamentals.
  • Familiarity with prompt engineering and LLM interaction patterns.
  • Understanding of RAG, embeddings, and semantic search.
  • Strong analytical and problem-solving skills.
  • Ability to experiment, evaluate results, and improve AI systems systematically.

Academic projects, internships, research, hackathons, GitHub projects, and personal Agentic AI projects can be considered relevant experience.

Nice to Have

  • Experience with LangGraph, LangChain, LlamaIndex, AutoGen, CrewAI, or similar frameworks.
  • Experience with OpenAI, Anthropic, Google Gemini, Meta Llama, or Mistral models.
  • Knowledge of tool calling and function calling.
  • Experience building multi-agent systems.
  • Knowledge of agent memory and state management.
  • Experience with RAG pipelines.
  • Familiarity with vector databases such as Pinecone, Weaviate, Qdrant, Chroma, or pgvector.
  • Experience with FastAPI or similar Python backend frameworks.
  • Knowledge of Docker and cloud platforms.
  • Experience integrating AI agents with third-party APIs.
  • Understanding of AI evaluation and observability.
  • Familiarity with MCP or other emerging agent-tool integration standards.
  • Experience building AI assistants, copilots, autonomous workflows, or AI automation systems.
  • Contributions to open-source AI projects or technical GitHub repositories.