Senior AI Engineer with 9+ years of software engineering experience, including 5+ years building production AI applications. I've developed multimodal AI systems, RAG platforms, AI agents, real-time voice assistants, and LLM-powered automation for healthcare and enterprise products. My work spans the full stack—from React/Next.js frontends to scalable Python/FastAPI backend services running on AWS and GCP.
I enjoy solving challenging AI infrastructure problems, including retrieval pipelines, agent orchestration, prompt engineering, semantic search, streaming AI, and low-latency inference. I have experience building production systems with LangChain, LangGraph, LlamaIndex, OpenAI, Claude, Gemini, and modern vector databases such as Pinecone, Weaviate, FAISS, and pgvector.
ben102327 · · focus · HN ↗
Remote: Yes
Willing to relocate: Yes
Technologies: Python, FastAPI, Node.js, React, Next.js, TypeScript, LangChain, LangGraph, LlamaIndex, OpenAI, Claude, Gemini, RAG, Agentic AI, Vector Databases (Pinecone, Weaviate, FAISS, pgvector), AWS (Bedrock, SageMaker, ECS, Lambda, EC2, S3), GCP, Docker, Kubernetes, PostgreSQL, Redis, Elasticsearch, Kafka, WebSockets, LiveKit, Deepgram, Whisper, ElevenLabs
Résumé/CV: <a href="https://drive.google.com/file/d/16OnzHA6ljIFV0jh4TCLdAMgB5__BaW94/view?usp=drive_link" rel="nofollow">https://drive.google.com/file/d/16OnzHA6ljIFV0jh4TCLdAMgB5__...
Email: benjaminkrueger1@outlook.com
Summary:
Senior AI Engineer with 9+ years of software engineering experience, including 5+ years building production AI applications. I've developed multimodal AI systems, RAG platforms, AI agents, real-time voice assistants, and LLM-powered automation for healthcare and enterprise products. My work spans the full stack—from React/Next.js frontends to scalable Python/FastAPI backend services running on AWS and GCP.
I enjoy solving challenging AI infrastructure problems, including retrieval pipelines, agent orchestration, prompt engineering, semantic search, streaming AI, and low-latency inference. I have experience building production systems with LangChain, LangGraph, LlamaIndex, OpenAI, Claude, Gemini, and modern vector databases such as Pinecone, Weaviate, FAISS, and pgvector.