Senior AI Agent Engineer — On-Site Houston

Harnham

Houston (TX)

On-site

USD 160,000 - 230,000

Full time

34 hours ago

Be an early applicant

Application generator

Get a reply from this employer — a resume and cover letter tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Harnham is seeking a Senior Agentic AI Software Engineer in Houston, TX to design, build, and deploy production-grade AI agents and agentic systems. You will own end-to-end AI agent workflows, integrate LLMs and tools, and ensure security, reliability, and performance in a production environment.

The role combines AI engineering with full-stack capabilities, including backend services in Python, RESTful APIs, and modern frontend interfaces.

Qualifications

Bachelor's degree in Computer Science, Software Engineering, or a related technical field.
8+ years of professional software engineering experience building production applications.
Strong backend/software engineering experience with Python and RESTful APIs.
Hands-on experience building LLM-powered applications, AI agents, or agentic workflows.
Experience designing systems involving LLMs, RAG, tool calling, agent orchestration, memory, state management, or context engineering.
Experience integrating AI systems with APIs, databases, enterprise applications, and external tools.
Strong understanding of software architecture, distributed systems, APIs, testing, and production engineering.
Experience with React, Angular, Next.js, or another modern frontend framework.
Experience building data-intensive applications and/or data pipelines.
Experience with Databricks, Lakehouse architectures, or similar modern data platforms preferred.
Experience with agent frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, or similar preferred.
Experience with MCP or other approaches to connecting AI agents with external tools and systems preferred.
Experience with cloud-native application development, preferably GCP.
Experience with CI/CD, infrastructure-as-code, observability, and production deployments.
Experience actively using AI coding tools such as Claude Code, Codex, or Augment Code preferred.

Responsibilities

Design, build, and deploy production-grade AI agents capable of executing complex, multi-step workflows.
Develop agentic systems that can reason over structured and unstructured data, select and invoke tools, interact with APIs and enterprise systems, and take actions on behalf of users.
Build intelligent support agents that can understand user intent, retrieve relevant information, maintain context, resolve requests, and elevate to human operators when required.
Design agent architectures including orchestration, planning, tool routing, state management, memory, and context management.
Develop multi-step and multi-agent workflows that combine LLMs, business logic, APIs, RAG, structured data, and external tools.
Build secure mechanisms for agents to interact with enterprise applications, databases, internal systems, and third-party services.
Implement guardrails, fallback mechanisms, permissions, and human-in-the-loop workflows for reliable production deployment.
Develop RAG systems that allow agents to retrieve and reason over enterprise knowledge and operational data.
Build retrieval, context, and memory pipelines to support agent performance and personalization.
Design prompting and context-engineering strategies for complex agentic workflows.
Integrate and orchestrate LLMs from providers such as OpenAI, Anthropic, or Google.
Evaluate models, agent architectures, retrieval strategies, and tool-use approaches based on accuracy, latency, cost, reliability, and task completion.
Develop automated evaluation frameworks and monitoring to measure agent quality and identify regressions.
Stay current with emerging agent frameworks, protocols, and architectures including LangGraph, LangChain, LlamaIndex, MCP, and similar technologies.