AI System Engineer

Innovative Consulting Inc (ICI); Atlanta (GA); On-site; USD 120,000 - 170,000; Full time

Job summary

Innovative Consulting Inc (ICI) is seeking an AI Systems Engineer to architect and implement AI-powered, end-to-end systems using Python frameworks and modern front-end tech. You will design prompts, manage context, and orchestrate intelligent agents across cloud environments.

The role emphasizes building scalable pipelines, integrating LLMs, and delivering production-grade solutions with cross-functional teams.

Qualifications

• Strong experience with Fullstack Python development (FastAPI, Flask, Django; SQL/NoSQL databases).
• Expertise in prompt engineering and context-aware LLM integration.
• Hands-on experience with LangGraph and MCP for agent orchestration and workflow design.
• Familiarity with vector search, RAG pipelines, and session/context management strategies.
• Experience integrating AI agents into production systems with cloud infrastructure (AWS, GCP, Azure).
• Proficiency with containerization (Docker), CI/CD pipelines, and scalable distributed systems.
• Excellent problem-solving, communication, and collaboration skills.

Responsibilities

• Design and optimize prompts for LLMs to ensure accurate, contextually rich outputs across diverse use cases.
• Architect dynamic context management systems including session memory, retrieval-augmented generation (RAG), and user personalization.
• Develop and deploy autonomous and semi-autonomous AI agents using LangGraph and MCP.
• Coordinate multi-agent workflows, manage state transitions, and ensure seamless model interoperability.
• Build robust backend services and APIs using Python frameworks (FastAPI, Flask, Django).
• Develop front-end interfaces using modern JS frameworks (React, Vue, Angular) to support end-to-end user experiences.
• Connect agents with external data sources, vector databases, third-party APIs, and ML models.
• Implement scalable pipelines for knowledge retrieval, model serving, and real-time interaction.
• Establish testing, monitoring, and evaluation pipelines to continuously improve agent performance and context handling.
• Optimize system reliability, latency, and scalability across cloud environments.
• Work cross-functionally with product managers, data scientists, and ML engineers to define requirements and deliver production-grade solutions.
• Contribute to architectural decisions, sprint planning, and iterative development cycles.

Skills

Fullstack Python

Prompt engineering

LLM integration

Cloud deployment

CI/CD

Docker

Team collaboration

Tools

LangGraph

MCP

FastAPI

Flask

Django

React

Vue

Angular

Docker

Job description

Location

Atlanta, Dallas, New Jersey, or Seattle

Role and Responsibilities

We are seeking versatile and highly skilled AI Systems Engineer with deep expertise in Fullstack Python development, intelligent agent orchestration, and advanced context engineering. This role is central to building next-generation AI-powered applications that leverage large language models (LLMs), multi-agent workflows, and dynamic context management. You will architect and integrate scalable systems using frameworks like LangGraph and MCP, while collaborating across disciplines to deliver adaptive, intelligent solutions.

Key Responsibilities

Prompt & Context Engineering

1. 2. Design and optimize prompts for LLMs to ensure accurate, contextually rich outputs across diverse use cases.
2. 3. Architect dynamic context management systems including session memory, retrieval-augmented generation (RAG), and user personalization.

Agent Integration & Orchestration

1. 5. Develop and deploy autonomous and semi-autonomous AI agents using LangGraph and MCP.
2. 6. Coordinate multi-agent workflows, manage state transitions, and ensure seamless model interoperability.

Fullstack System Development

1. 1. Build robust backend services and APIs using Python frameworks (FastAPI, Flask, Django).
2. 2. Develop front-end interfaces using modern JS frameworks (React, Vue, Angular) to support end-to-end user experiences.

System Integration

1. 1. Connect agents with external data sources, vector databases, third-party APIs, and ML models.
2. 2. Implement scalable pipelines for knowledge retrieval, model serving, and real-time interaction.

Evaluation & Optimization

1. 1. Establish testing, monitoring, and evaluation pipelines to continuously improve agent performance and context handling.
2. 2. Optimize system reliability, latency, and scalability across cloud environments.

Work cross-functionally with product managers, data scientists, and ML engineers to define requirements and deliver production-grade solutions.

Contribute to architectural decisions, sprint planning, and iterative development cycles.

Required Skills & Qualifications

1. 1. Strong experience with Fullstack Python development (FastAPI, Flask, Django; SQL/NoSQL databases).
2. 2. Proven expertise in prompt engineering and context-aware LLM integration (OpenAI, Anthropic, open-source models).
3. 3. Hands-on experience with LangGraph and MCP for agent orchestration and workflow design.
4. 4. Familiarity with vector search, RAG pipelines, and session/context management strategies.
5. 5. Experience integrating AI agents into production systems with cloud infrastructure (AWS, GCP, Azure).
6. 6. Proficiency with containerization (Docker), CI/CD pipelines, and scalable distributed systems.
7. 7. Excellent problem-solving, communication, and collaboration skills.

Preferred Qualifications

1. 1. Background in information retrieval, knowledge graphs, or search systems.
2. 2. Experience with front-end development and data visualization tools.
3. 3. Contributions to open-source AI, agent, or LLM frameworks.
4. 4. Familiarity with advanced ML model serving and orchestration platforms