Senior AI Engineer

Avanciers Inc.; United States; On-site; USD 140,000 - 190,000; Full time

Job summary

Avanciers Inc. is recruiting for a Senior AI Engineer for a premier client in the USA, with location flexibility including remote work. You will own end-to-end development of LLM-powered applications and AI workflows, focusing on architecture, development, deployment, and optimization of intelligent solutions.

The role demands strong Python, LLM/AI orchestration, RAG architectures, embeddings, and cloud-based backend experience. You will collaborate with teams to deliver scalable AI systems.

Qualifications

• Strong Python programming skills with production-grade backend experience.
• Proven experience building LLM-powered applications and AI solutions.
• Deep understanding of Generative AI, LLMs, prompt engineering, and orchestration.
• Experience designing and implementing RAG architectures.
• Experience with embeddings and vector databases.
• Hands-on experience building AI agents and agentic workflows.
• Exposure to LangChain, LangGraph, or AutoGen frameworks.
• Strong system design and software architecture skills.
• Experience integrating AI with APIs, backends and enterprise data.
• Awareness of production considerations: performance, reliability, latency, cost.

Responsibilities

• Architect and develop end-to-end LLM-powered applications and agentic AI workflows using Python.
• Design RAG pipelines using enterprise data, embeddings, and vector databases.
• Build multi-step AI agents supporting planning, memory, and reasoning.
• Develop AI solutions with LangChain, LangGraph, and AutoGen.
• Integrate AI systems with REST APIs, backend services, and cloud platforms.
• Implement prompt engineering, LLM orchestration, and AI workflow automation.
• Design scalable backend architectures for AI-powered apps.
• Define evaluation metrics for accuracy, latency, and cost optimization.
• Monitor production AI systems for performance and reliability.
• Collaborate with engineering and business teams to translate requirements.

Skills

Python programming

LLM-powered apps

prompt engineering

AI orchestration

RAG architectures

embeddings & vector DB

AI agents & workflows

cloud-based apps

system design

REST APIs & backend

Education

Bachelor's degree

Tools

LangChain

LangGraph

AutoGen

Job description

Avanciers is a premier IT Staffing/Consulting organization and we are currently recruiting for a Full-Time role for one of our premier client in USA for Senior AI Engineer

Job Type: Full-Time

Location: Anywhere in the U.S. / Remote

Job Overview

We are seeking a Senior AI Engineer to design, develop, and deploy production-grade LLM-powered applications and agentic AI systems. The ideal candidate will have strong expertise in Python, Large Language Models (LLMs), RAG architectures, AI agents, modern AI frameworks, and scalable cloud-based systems.

This role will be responsible for owning the end-to-end development of intelligent solutions, from architecture and development through deployment, evaluation, and optimization.

Key Responsibilities

• Architect and develop end-to-end LLM-powered applications and agentic AI workflows using Python.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines using enterprise data, embeddings, and vector databases.
• Build multi-step, tool-using AI agents supporting planning, execution, memory, and reasoning.
• Develop AI solutions using modern frameworks such as LangChain, LangGraph, and AutoGen.
• Integrate LLM and AI systems with REST APIs, backend services, enterprise applications, and cloud platforms.
• Implement prompt engineering, LLM orchestration, and AI workflow automation.
• Design scalable and reliable backend architectures for AI-powered applications.
• Establish strategies for AI evaluation, accuracy, reliability, latency, scalability, and cost optimization.
• Monitor and optimize production AI systems to ensure performance and reliability.
• Collaborate with engineering and business teams to translate requirements into scalable AI solutions.

Required Qualifications

• Strong Python programming skills with experience developing production-grade backend systems.
• Hands-on experience building and deploying LLM-powered applications.
• Strong understanding of Generative AI, LLMs, prompt engineering, and AI orchestration.
• Proven experience designing and implementing RAG architectures.
• Experience working with embeddings and vector databases.
• Hands-on experience developing AI agents and agentic workflows.
• Experience with frameworks such as LangChain, LangGraph, or AutoGen.
• Strong system design and software architecture skills.
• Experience building and scaling cloud-based applications and services.
• Experience integrating AI solutions with APIs, backend systems, and enterprise data sources.
• Strong understanding of production considerations including performance, reliability, scalability, accuracy, latency, and cost.

Preferred Qualifications

• Experience with multiple LLM providers and APIs.
• Experience with cloud platforms such as AWS, Azure, or Google Cloud.
• Experience with containerization and modern application deployment practices.
• Knowledge of AI/ML evaluation frameworks and observability.
• Experience working with enterprise-scale data and AI applications.
• Strong problem-solving, communication, and collaboration skills.

Education & Work Authorization

• Bachelor’s degree or foreign equivalent from an accredited institution is preferred. Equivalent professional experience may be considered.
• Candidates must be authorized to work in the United States without current or future employer-based visa sponsorship.
• The position may require occasional relocation and/or travel depending on project requirements.