Job Role : AI engineer (Agents, LLM gateway, mode integration, SDK)
Hire Type : Contract
Project Duration : 12+ months, with extension
Location :- Plano, TX (Hybrid)
Job Description:-
Position Overview
We are seeking an experienced AI Engineer to design, develop, and integrate AI-powered applications, intelligent agents, and Large Language Model (LLM) solutions. The ideal candidate should have hands-on experience with AI agents, LLM gateways, model integration, and AI/ML SDKs.
Key Responsibilities
- Design and develop AI-powered applications and autonomous AI agents.
- Build and integrate LLM-based solutions using leading AI/ML models and platforms.
- Develop and manage LLM Gateway solutions for centralized model access, routing, security, monitoring, and governance.
- Integrate multiple foundation models and LLM providers through APIs and SDKs.
- Develop agent workflows involving tool calling, function calling, memory, RAG, and multi-agent orchestration.
- Work with AI/ML SDKs, APIs, and frameworks to accelerate application development.
- Integrate AI models into existing enterprise applications and technology platforms.
- Implement prompt engineering, model evaluation, response optimization, and guardrails.
- Collaborate with software engineers, data engineers, architects, and product teams to deliver production-ready AI solutions.
- Troubleshoot performance, scalability, latency, security, and integration issues across AI applications.
- Follow best practices for AI security, responsible AI, observability, and governance.
Required Skills
- Strong hands-on experience as an AI Engineer / Generative AI Engineer.
- Experience developing and integrating AI Agents and Agentic AI solutions.
- Strong knowledge of LLMs, Generative AI, Prompt Engineering, RAG, and Vector Databases.
- Experience with LLM Gateway / AI Gateway concepts and implementations.
- Hands-on experience integrating multiple LLM/model providers through APIs.
- Strong experience with AI/ML SDKs and APIs.
- Experience with agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or similar.
- Strong programming experience in Python.
- Experience with REST APIs, microservices, JSON, and cloud-based AI services.
- Understanding of model authentication, authorization, rate limiting, monitoring, and governance.
- Experience deploying AI solutions in enterprise or production environments.
Preferred Skills
- Experience with AWS, Azure, or Google Cloud AI services.
- Knowledge of OpenAI, Azure OpenAI, Anthropic, Gemini, or other foundation models.
- Experience with Docker, Kubernetes, CI/CD, and cloud-native architectures.
- Knowledge of AI observability, model evaluation, and security.
- Experience with enterprise-scale AI platform integration.