AI Engineer

As a Senior AI Engineer / Data Engineer at STAND 8, you will play a crucial role in contributing to the development of AI-powered business solutions. Your work will involve leveraging advanced large language models, real-time AI interactions, and cutting-edge retrieval architectures to revolutionize business operations in recruitment, data extraction, and intelligent decision-making. **Responsibilities:** - Design, construct, and enhance AI-powered systems incorporating text, voice, and visual elements. - Integrate and deploy LLM APIs from providers like OpenAI, Anthropic, and AWS Bedrock. - Develop and manage RAG systems with hybrid search, re-ranking, and knowledge graphs. - Implement real-time AI functionalities using streaming analytics and voice interaction tools such as ElevenLabs. - Create APIs and pipelines with frameworks like FastAPI to streamline AI workflows. - Process and evaluate unstructured documents considering layout and semantics. - Build predictive models to drive intelligent business recommendations. - Deploy scalable solutions utilizing AWS services such as EC2, S3, RDS, Lambda, and Bedrock. - Utilize Docker for containerization and oversee CI/CD workflows and version control through Git. - Debug, monitor, and optimize performance for large-scale data pipelines. - Collaborate effectively with product, data, and engineering teams across various functions. **Qualifications:** - 5+ years of experience in AI/ML or data engineering with Python in production environments. - Hands-on familiarity with LLM APIs and frameworks like OpenAI, Anthropic, Bedrock, or LangChain. - Previous experience deploying vector databases such as PGVector, Weaviate, FAISS, or Pinecone in production. - Strong understanding of NLP, document extraction, and text processing. - Proficiency in AWS cloud services including Bedrock, EC2, S3, Lambda, and monitoring tools. - Experience with FastAPI or similar frameworks for building AI/ML APIs. - Knowledge of embedding models, prompt engineering, and RAG systems. - Proficiency in asynchronous programming for high-throughput pipelines. - Strong skills in Docker, Git workflows, CI/CD pipelines, and adherence to testing best practices. **Preferred:** - Background in HRTech or ATS integrations like Greenhouse, Workday, Bullhorn. - Experience with knowledge graphs such as Neo4j for semantic relationships. - Exposure to real-time AI systems like WebRTC, OpenAI Realtime API, and voice AI tools such as ElevenLabs. - Advanced Python development skills with clean architecture and design patterns. - Experience in large-scale data processing with cost optimization techniques for LLMs. - Proficiency in event-driven architecture using AWS SQS, SNS, or EventBridge. - Hands-on experience in fine-tuning, evaluating, and deploying foundation models.,