Senior AI Engineer

Zenith System Solutions; Plano (TX); On-site; USD 140,000 - 190,000; Full time

Job summary

Zenith System Solutions is seeking a Generative AI Engineer with 7–10+ years of hands-on experience to design scalable AI-powered microservices and APIs using Python and FastAPI. You will build enterprise-grade RAG solutions, develop intelligent agentic workflows, and optimize retrieval and context orchestration on Azure.

Collaboration with product, engineering, and business teams is essential for production-ready AI solutions.

Qualifications

• 7–10+ years of software engineering experience with Python.
• Experience designing microservices-based architectures using Python frameworks (FastAPI or similar).
• Experience building scalable, secure, production-grade APIs.
• Strong experience with Microsoft Azure including AI, data, and application services.
• Expertise in MongoDB or NoSQL data modeling and optimization.
• Experience deploying cloud-native apps and containerized workloads.
• Hands-on experience with AI Agents, multi-agent systems and autonomous workflows.
• Knowledge of Retrieval-Augmented Generation (RAG) architectures and context-aware retrieval pipelines.
• Familiarity with AI Observability platforms (e.g., Arize AI) and DeepEval.
• Experience with vector databases, LangGraph, Semantic Kernel, and governance considerations.
• MLOps/LLMOps practices, CI/CD pipelines, and model lifecycle management.

Responsibilities

• Design and develop scalable AI-powered microservices and APIs using Python and FastAPI.
• Build and maintain enterprise-grade RAG and Graph RAG solutions.
• Develop intelligent agentic workflows leveraging organizational knowledge and business context.
• Optimize knowledge retrieval, context orchestration, and response quality for AI apps.
• Implement evaluation frameworks and monitoring using DeepEval and Arize.
• Deploy, monitor, and maintain AI apps on Azure.
• Collaborate with product, engineering, and business teams to translate use cases into production AI solutions.

Skills

Python programming

Microservices architecture

API design & security

Azure cloud services

NoSQL databases

Tools

Kubernetes

Docker

GitHub Actions

Azure DevOps

Semantic Kernel

LangGraph

Neo4j

LangChain

LlamaIndex

Job description

• 8+ years of experience in software engineering with strong expertise in Python.
• Hands-on experience designing and developing microservices-based architectures using FastAPI or similar Python frameworks.
• Experience building scalable, secure, and production-grade APIs.
• Strong experience with Microsoft Azure, including AI, data, and application services.
• Expertise in MongoDB and NoSQL database design, optimization, and data modeling.
• Experience deploying and managing cloud-native applications and containerized workloads.

Generative AI & Agentic Systems

• Hands-on experience building AI Agents, multi-agent systems, and autonomous workflows.
• Strong understanding of Retrieval-Augmented Generation (RAG) architectures, including:
  • Knowledge RAG
  • Graph RAG
  • Hybrid retrieval systems
  • Context-aware retrieval pipelines
• Experience designing enterprise knowledge bases, semantic search solutions, and context-building frameworks.
• Strong understanding of Large Language Models (LLMs) and Small Language Models (SLMs).
• Experience with model selection, prompt engineering, grounding strategies, fine-tuning approaches, and inference optimization.
• Familiarity with model performance, latency, cost optimization, and governance considerations.

AI Evaluation & Observability

• Hands-on experience implementing Agentic Evaluation frameworks, including tools such as DeepEval.
• Answer relevance
• Agent task completion
• Safety and reliability
• Experience with AI observability and monitoring platforms, particularly Arize AI, for production monitoring, tracing, and model performance analysis.

Preferred Qualifications

• Experience with vector databases and embedding models.
• Familiarity with LangChain, LangGraph, Semantic Kernel, LlamaIndex, or similar AI orchestration frameworks.
• Experience building enterprise AI applications with governance, security, and compliance considerations.
• Knowledge of MLOps/LLMOps practices, CI/CD pipelines, and model lifecycle management.

Key Responsibilities

• Design and develop scalable AI-powered microservices and APIs using Python and FastAPI.
• Build and maintain enterprise-grade RAG and Graph RAG solutions.
• Develop intelligent agentic workflows that leverage organizational knowledge and business context.
• Optimize knowledge retrieval, context orchestration, and response quality for AI applications.
• Implement evaluation frameworks and monitoring solutions using DeepEval and Arize.
• Deploy, monitor, and maintain AI applications on Azure.
• Collaborate with product, engineering, and business teams to translate use cases into production-ready AI solutions.

Must Have Existing Hands-On Experience

• Semantic Kernel
• LangGraph
• Neo4j or Graph Databases
• Kubernetes and Docker
• GitHub Actions / Azure DevOps

Additional Note:

This version is targeted at a S Generative AI Engineer (7-10+ years experience).