AI Software Engineer - End-to-End Production ML & RAG

Oteemo Inc.; Reston (VA); On-site; USD 140,000 - 190,000; Full time

Job summary

Oteemo Inc. seeks an AI Software Engineer to design and ship enterprise AI applications end-to-end, from database to UI. You will leverage LLMs, RAG systems, and production ML infrastructure to deliver scalable, cost-efficient AI features for enterprise clients.

You will work across backend Python/FastAPI, frontend React/Next.js, and data stores like PostgreSQL, MongoDB, and Redis, with Docker, Kubernetes, and CI/CD pipelines to ensure robust, secure deployments.

Qualifications

• Expert-level proficiency in Python with modern frameworks (FastAPI, Flask).
• Strong TypeScript/JavaScript skills with deep React and Next.js experience; proven track record designing and building RESTful and GraphQL APIs.
• Solid understanding of relational (PostgreSQL, MySQL) and NoSQL (MongoDB) databases.
• Experience with authentication systems (OAuth2, JWT, SSO) and security best practices.
• Proven track record of shipping high-quality, scalable software to production.
• Hands-on experience building and deploying AI/ML applications in production environments.
• Deep understanding of LLM integration, prompt engineering, and context management.
• Proven expertise with RAG systems, including document processing, chunking, embedding, retrieval, and generation.
• Experience working with vector databases (Pinecone, Weaviate, Chroma, FAISS, or Qdrant).
• Strong grasp of semantic search, similarity algorithms, and hybrid search techniques.
• Knowledge of evaluation frameworks for assessing AI system quality and performance.
• Production experience with Docker containerization and Kubernetes orchestration.
• Strong knowledge of at least one major cloud platform (AWS, Azure, or GCP) and its AI services.
• Experience building CI/CD pipelines for ML/AI application.
• Proficiency with infrastructure as code tools (Terraform, CloudFormation, Pulumi).
• Understanding of monitoring, logging, and alerting best practices; cost optimization experience for cloud and AI workloads.
• Strong computer science fundamentals and algorithmic thinking.
• Proficiency with Git workflows, code review practices, and collaborative development.
• Excellent debugging and problem-solving skills.
• Clear technical communication and documentation abilities.

Responsibilities

• Design end-to-end RAG (Retrieval-Augmented Generation) pipelines for intelligent document search and question-answering across enterprise knowledge bases.
• Build production-ready integrations with leading LLMs (GPT-4, Claude, Gemini) for accurate, contextual responses to user queries.
• Develop prompt engineering strategies and evaluation frameworks to ensure consistent, high-quality AI outputs.
• Create agent systems with tool integration capabilities that can autonomously complete complex tasks.
• Implement vector search solutions using Pinecone, Weaviate, or similar technologies for semantic similarity and knowledge retrieval.
• Build scalable backend services using Python/FastAPI with type-safe APIs, authentication, and robust error handling.
• Develop responsive, performant frontend applications using React/Next.js with real-time streaming for LLM responses.
• Design and optimize database schemas across PostgreSQL, MongoDB, and Redis to support high-throughput AI workloads.
• Implement WebSocket servers and event-driven architectures for real-time user experiences.
• Create comprehensive testing strategies covering unit, integration, and end-to-end tests.
• Deploy and manage ML/AI services using Docker containers and Kubernetes orchestration.
• Build and maintain CI/CD pipelines for rapid, safe deployment of AI features.
• Implement infrastructure as code using Terraform to manage cloud resources (AWS, Azure, or GCP).
• Set up monitoring and observability using Datadog, Prometheus/Grafana, and LLM-specific tools (LangSmith, Weights & Biases).
• Optimize costs through intelligent caching, batching strategies, and model selection algorithms.
• Ensure enterprise-grade security through authentication, authorization, secrets management, and compliance measures.

Skills

Python

TypeScript/JavaScript

React/Next.js

APIs REST/GraphQL

LLM integration

RAG systems

Docker/Kubernetes

CI/CD

Terraform

Pinecone/Weaviate

Vector databases

Cloud AI services

Security/auth

Tools

FastAPI

Flask

PostgreSQL

MongoDB

Redis

Weaviate

Pinecone

FAISS

LangSmith

Weights & Biases

Datadog

Grafana

Kubernetes

Docker

Job description

Oteemo Inc. seeks an AI Software Engineer to design and ship enterprise AI applications end-to-end, from database to UI. You will leverage LLMs, RAG systems, and production ML infrastructure to deliver scalable, cost-efficient AI features for enterprise clients.

You will work across backend Python/FastAPI, frontend React/Next.js, and data stores like PostgreSQL, MongoDB, and Redis, with Docker, Kubernetes, and CI/CD pipelines to ensure robust, secure deployments.