Oteemo Inc.
Full Stack Engineer - Enterprise AI Applications (Richmond)
Oteemo Inc., Richmond, Virginia, United States, 23214
Full Stack Engineer - Enterprise AI Applications
Experience Level: Mid Level 4+ years
Location: Richmond, VA (Hybrid)
Work Authorization/Clearance Requirements: NA
Roles and Responsibilities of this position: Overview We're seeking an exceptional Full Stack Engineer to build and scale our enterprise AI applications. You'll design and implement complete AI-powered features from database to UI, working with cutting-edge LLM technology, RAG systems, and production ML infrastructure. This role combines full-stack development expertise with hands-on AI/ML engineering, deploying intelligent systems that deliver real business value at scale.
You'll be a key technical contributor, shipping production-ready AI features that users love while ensuring reliability, performance, and cost-effectiveness. This is an opportunity to work at the intersection of software engineering and artificial intelligence, solving complex problems with modern technology.
What Youll Build AI Applications Design end-to-end RAG pipelines for intelligent search and enterprise Q&A Integrate production-grade LLM solutions (GPT-4, Claude, Gemini) Develop prompt strategies, evaluation frameworks, and structured output workflows Build autonomous agents with tool-use capabilities Implement vector search using Pinecone, Weaviate, Chroma, FAISS, or Qdrant Full-Stack Features Build scalable backend services with Python/FastAPI Develop performant UIs in React/Next.js with real-time LLM streaming Design optimized databases across PostgreSQL, MongoDB, Redis Implement WebSockets, event-driven systems, and comprehensive test coverage Production Infrastructure Deploy AI services using Docker & Kubernetes Build CI/CD pipelines for rapid, reliable releases Manage IaC with Terraform on AWS/Azure/GCP Set up monitoring/observability (Datadog, Prometheus, LangSmith, W&B) Ensure security best practices and cost-efficient AI operations Required Experience Full-Stack Development (4+ yrs) Strong Python (FastAPI/Flask) and TypeScript/React/Next.js REST/GraphQL API design, authentication, and security best practices Experience with relational & NoSQL databases Proven delivery of scalable production systems AI/ML Engineering (3+ yrs) Hands-on LLM integration, prompt engineering, and context management Strong experience with RAG (chunking, embeddings, retrieval, generation) Proficiency with vector DBs and semantic/hybrid search Knowledge of AI evaluation frameworks MLOps & Cloud (3+ yrs) Docker, Kubernetes, CI/CD for ML workloads Cloud platforms (AWS/Azure/GCP) and IaC (Terraform/Pulumi) Monitoring, logging, alerting, and cost optimization Engineering Excellence Strong CS fundamentals, problem-solving, debugging TDD, Git workflows, code reviews, clean documentation Comfortable in fast-paced Agile environments Preferred Qualifications Experience with LangChain, LlamaIndex, LangGraph, agent frameworks Exposure to LoRA/QLoRA fine-tuning, multimodal AI, MCP Experience with Kafka/RabbitMQ, graph DBs (Neo4j) Open-source contributions Mentorship, architectural decision-making, cross-team collaboration Tech Stack Exposure (Preferred) Python, Pandas, ML/DL/NLP/GPT-based workflows OpenAI, HuggingFace, Claude, Cohere, Mistral Agentic AI (LangGraph, CrewAI, AutoGen, LangChain Agents) Docker, Kubernetes, Git, CI/CD
Roles and Responsibilities of this position: Overview We're seeking an exceptional Full Stack Engineer to build and scale our enterprise AI applications. You'll design and implement complete AI-powered features from database to UI, working with cutting-edge LLM technology, RAG systems, and production ML infrastructure. This role combines full-stack development expertise with hands-on AI/ML engineering, deploying intelligent systems that deliver real business value at scale.
You'll be a key technical contributor, shipping production-ready AI features that users love while ensuring reliability, performance, and cost-effectiveness. This is an opportunity to work at the intersection of software engineering and artificial intelligence, solving complex problems with modern technology.
What Youll Build AI Applications Design end-to-end RAG pipelines for intelligent search and enterprise Q&A Integrate production-grade LLM solutions (GPT-4, Claude, Gemini) Develop prompt strategies, evaluation frameworks, and structured output workflows Build autonomous agents with tool-use capabilities Implement vector search using Pinecone, Weaviate, Chroma, FAISS, or Qdrant Full-Stack Features Build scalable backend services with Python/FastAPI Develop performant UIs in React/Next.js with real-time LLM streaming Design optimized databases across PostgreSQL, MongoDB, Redis Implement WebSockets, event-driven systems, and comprehensive test coverage Production Infrastructure Deploy AI services using Docker & Kubernetes Build CI/CD pipelines for rapid, reliable releases Manage IaC with Terraform on AWS/Azure/GCP Set up monitoring/observability (Datadog, Prometheus, LangSmith, W&B) Ensure security best practices and cost-efficient AI operations Required Experience Full-Stack Development (4+ yrs) Strong Python (FastAPI/Flask) and TypeScript/React/Next.js REST/GraphQL API design, authentication, and security best practices Experience with relational & NoSQL databases Proven delivery of scalable production systems AI/ML Engineering (3+ yrs) Hands-on LLM integration, prompt engineering, and context management Strong experience with RAG (chunking, embeddings, retrieval, generation) Proficiency with vector DBs and semantic/hybrid search Knowledge of AI evaluation frameworks MLOps & Cloud (3+ yrs) Docker, Kubernetes, CI/CD for ML workloads Cloud platforms (AWS/Azure/GCP) and IaC (Terraform/Pulumi) Monitoring, logging, alerting, and cost optimization Engineering Excellence Strong CS fundamentals, problem-solving, debugging TDD, Git workflows, code reviews, clean documentation Comfortable in fast-paced Agile environments Preferred Qualifications Experience with LangChain, LlamaIndex, LangGraph, agent frameworks Exposure to LoRA/QLoRA fine-tuning, multimodal AI, MCP Experience with Kafka/RabbitMQ, graph DBs (Neo4j) Open-source contributions Mentorship, architectural decision-making, cross-team collaboration Tech Stack Exposure (Preferred) Python, Pandas, ML/DL/NLP/GPT-based workflows OpenAI, HuggingFace, Claude, Cohere, Mistral Agentic AI (LangGraph, CrewAI, AutoGen, LangChain Agents) Docker, Kubernetes, Git, CI/CD