Senior AI/LLM Engineer

Title: Senior AI/LLM Engineer

Location: Pittsburgh, Pennsylvania (Remote)

Type: Contract

Project Overview

• We are seeking an experienced [strong style="font-weight: bolder;Senior AI/LLM Engineer to design, develop, and deploy enterprise-grade Generative AI solutions that leverage Large Language Models (LLMs) to solve complex business challenges.
• The ideal candidate will have strong expertise in Python development, Retrieval-Augmented Generation (RAG), AI orchestration frameworks, and cloud-native AI architectures.
• This role will work closely with product owners, solution architects, data engineers, and business stakeholders to build scalable, secure, and production-ready AI applications powered by OpenAI and other leading foundation models.

Key Responsibilities:

AI Solution Design & Development

• Design, develop, and deploy enterprise-scale Generative AI applications using modern LLM technologies.
• Build production-grade backend services using Python and modern software engineering practices.
• Develop scalable AI architectures utilizing OpenAI, Anthropic Claude, Gemini, Llama, or similar foundation models.
• Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases and semantic search capabilities.
• Develop intelligent multi-agent AI systems capable of orchestrating complex business workflows.
• AI Architecture & Integration
• Design AI solution architectures that are scalable, secure, maintainable, and aligned with enterprise standards.
• Integrate AI capabilities into existing enterprise applications, APIs, and business workflows.
• Develop and consume REST APIs, microservices, and event-driven services for AI applications.
• Implement AI orchestration frameworks such as LangChain and related agent frameworks.
• Prompt Engineering & Model Optimization
• Develop and optimize prompts for improved accuracy, reasoning, and business outcomes.
• Evaluate LLM performance and implement techniques to improve response quality.
• Establish AI governance, model evaluation, and responsible AI best practices.
• Monitor AI application performance and continuously optimize latency, cost, and quality.
• Cloud & Enterprise AI
• Build cloud-native AI solutions using Azure or AWS AI services.
• Implement Azure AI Search and vector search capabilities.
• Design secure enterprise AI applications following cloud security and governance standards.
• Collaborate with DevOps teams to deploy AI solutions using CI/CD pipelines.
• Stakeholder Collaboration
• Partner with business stakeholders to understand AI use cases and translate them into scalable technical solutions.
• Present architecture decisions, solution approaches, and AI strategies to both technical and non-technical audiences.
• Mentor junior engineers and contribute to AI engineering best practices across the organization.

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field.
• 6+ years of software engineering or machine learning engineering experience.
• Minimum 3+ years of hands-on experience building Artificial Intelligence and Generative AI solutions.
• 3 to 5 years of strong hands-on experience developing production applications using Python.
• 1 to 3 years of experience building applications using OpenAI (preferred), Anthropic Claude, Gemini, Llama, or similar LLM platforms.
• 3+ years of strong experience implementing Retrieval-Augmented Generation (RAG) architectures.
• 1 to 3 years of experience integrating vector databases and semantic search solutions.
• 1 to 3 years of strong understanding of LangChain and AI orchestration frameworks.
• Experience designing multi-agent AI architectures.
• Strong knowledge of prompt engineering, model evaluation, AI governance, and Responsible AI principles.
• Experience building REST APIs, microservices, and event-driven architectures.
• Experience with Azure or AWS cloud platforms.
• Strong understanding of scalable enterprise application architecture.
• Excellent analytical, problem-solving, and communication skills.
• Required Technical Skills
• Python
• JavaScript
• Generative AI
• Large Language Models (LLMs)
• OpenAI (Preferred)
• Retrieval-Augmented Generation (RAG)
• Multi-Agent AI Orchestration
• LangChain
• Langfuse
• AI Solution Architecture
• Azure AI Search
• Vector Databases
• Prompt Engineering
• REST APIs
• Microservices
• Event-Driven Architecture
• Azure or AWS Cloud Services
• Preferred Qualifications
• Experience with LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar AI agent frameworks.
• Experience with vector databases such as Pinecone, Weaviate, ChromaDB, Qdrant, Milvus, or Azure AI Search.
• Experience with containerization technologies such as Docker and Kubernetes.
• Knowledge of CI/CD pipelines and MLOps practices.
• Experience with AI observability and monitoring platforms.
• Familiarity with enterprise security, compliance, and Responsible AI frameworks.
• Experience working in Agile/Scrum environments.
• Nice to Have
• Experience developing enterprise copilots or AI assistants.
• Experience integrating AI into enterprise SaaS platforms.
• Knowledge of AI governance, security, and compliance standards.
• Experience optimizing LLM inference performance and AI operational costs.