AI Engineer Or Data Scientist

Company Description

ProjectsForce is a comprehensive field service management platform tailored for home improvement contractors, construction businesses, and property maintenance teams. By integrating tools for automating operations, scheduling jobs, managing contractors, and improving client communication, our platform enhances productivity and customer satisfaction. Whether it's HVAC, plumbing, landscaping, or roofing, ProjectsForce empowers businesses to streamline operations and scale confidently. Our innovative solutions are designed to simplify field management tasks, helping clients grow their businesses efficiently.

Role Description

We are seeking a highly skilled Data Scientist / AI Engineer with deep expertise in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks to design and build an intelligent chatbot platform. The solution will power scheduling and order management workflows, leveraging data stored in MySQL databases and integrating with real-time communication systems (voice and messaging). The ideal candidate will have strong experience in NLP, applied AI systems, and production‑grade deployments, with the ability to design scalable, tool‑augmented AI agents.

Key Responsibilities

• Design, develop, and optimize AI-driven chatbot systems using LLMs and RAG architectures
• Implement retrieval-based and generative AI pipelines for accurate and context-aware responses
• Build and orchestrate Agentic AI workflows using frameworks such as LangGraph, CrewAI, or AWS Bedrock Agents
• Design and implement tooling layers for LLMs, enabling structured API calling, function execution, and workflow automation
• Work with MySQL databases to extract, transform, and serve structured data for AI interactions
• Develop and optimize embeddings and vector search pipelines for high-relevance retrieval
• Fine-tune and customize LLM behavior for domain-specific use cases (scheduling, order lifecycle, customer interactions)
• Integrate chatbot systems with communication platforms (e.g., voice via Vapi, SMS/voice via Twilio)
• Collaborate with backend and platform teams to deploy AI services on AWS (Fargate, Lambda)
• Monitor, evaluate, and continuously improve model performance using feedback loops and analytics
• Ensure data security, privacy compliance, and system reliability in production environments

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Data Science, AI, or related field
• 5+ years of experience in NLP, machine learning, or applied AI systems
• Strong hands‑on experience with LLMs (GPT, LLaMA, Mistral, Claude, etc.)
• Proven experience building RAG‑based systems in production
• Proficiency in Python and modern AI orchestration frameworks (e.g., LangChain or similar)
• Experience with Agentic AI frameworks such as LangGraph, CrewAI, or AWS Bedrock
• Strong understanding of tool calling / function calling patterns for LLMs
• Solid experience with MySQL (query optimization, indexing, schema design)
• Experience with vector databases (FAISS, Pinecone, ChromaDB, Weaviate, etc.)
• Experience deploying AI services using Docker and AWS (Fargate, Lambda)
• Strong understanding of embeddings, retrieval mechanisms, and prompt engineering