AI Engineer

STAND 8 provides end-to-end IT solutions to enterprise partners across the United States and with offices in Los Angeles, New York, New Jersey, Atlanta, and more including internationally in Mexico and India. We are looking for a Senior AI Engineer / Data Engineer to be a part of our engineering team and contribute to building the future of AI-powered business solutions. In this role, you will be involved in developing intelligent systems that make use of advanced large language models (LLMs), real-time AI interactions, and cutting-edge retrieval architectures. Your efforts will have a direct impact on products that are revolutionizing business operations, particularly in the areas of recruitment, data extraction, and intelligent decision-making. This position offers an exciting opportunity for individuals who excel in constructing production-grade AI systems and are adept at working across the full spectrum of modern AI technologies. Responsibilities - Design, construct, and enhance AI-powered systems utilizing multi-modal architectures encompassing text, voice, and visual elements. - Incorporate and deploy LLM APIs sourced from providers like OpenAI, Anthropic, and AWS Bedrock. - Develop and manage RAG (Retrieval-Augmented Generation) systems featuring hybrid search, re-ranking, and knowledge graphs. - Create real-time AI functionalities through the utilization of streaming analytics and voice interaction tools such as ElevenLabs. - Establish APIs and pipelines using FastAPI or similar frameworks to facilitate AI workflows. - Process and evaluate unstructured documents with an understanding of layout and semantics. - Implement predictive models that drive intelligent business recommendations. - Deploy and sustain scalable solutions leveraging AWS services like EC2, S3, RDS, Lambda, Bedrock, among others. - Utilize Docker for containerization and oversee CI/CD workflows and version control via Git. - Debug, monitor, and optimize performance for large-scale data pipelines. - Collaborate seamlessly with product, data, and engineering teams across different functions. Qualifications - Possess 5+ years of experience in AI/ML or data engineering utilizing Python in production environments. - Hands-on familiarity with LLM APIs and frameworks such as OpenAI, Anthropic, Bedrock, or LangChain. - Previous experience in deploying vector databases like PGVector, Weaviate, FAISS, or Pinecone in production settings. - Solid grasp 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 constructing AI/ML APIs. - Knowledge of embedding models, prompt engineering, and RAG systems. - Proficiency in asynchronous programming for high-throughput pipelines. - Proficiency in Docker, Git workflows, CI/CD pipelines, and adherence to testing best practices. Preferred - Background in HRTech or ATS integrations (e.g., Greenhouse, Workday, Bullhorn). - Experience working with knowledge graphs (e.g., Neo4j) for semantic relationships. - Exposure to real-time AI systems (e.g., WebRTC, OpenAI Realtime API) and voice AI tools (e.g., ElevenLabs). - Advanced Python development skills employing design patterns and clean architecture. - Experience in large-scale data processing (1-2M+ records) with cost optimization techniques for LLMs. - Proficiency in event-driven architecture utilizing AWS SQS, SNS, or EventBridge. - Hands-on experience with fine-tuning, evaluating, and deploying foundation models.,