Senior AI Engineer

NovoEd, Inc.; United States; Remote; USD 140,000 - 200,000; Full time

Job summary

NovoEd, Inc. is seeking a senior-level AI Engineer to design, build, and deploy production-grade AI-powered backend systems.

You will integrate LLMs and machine learning models, optimize vector databases, and ensure low-latency performance across backend, AI inference, and UI layers. You’ll work with a fast-growing product team to ship practical, reliable AI features, balancing speed and reliability while maintaining a production-grade codebase.

Qualifications

• 3–5+ years backend engineering in Python with production apps.
• Masters degree in a related field.
• Proven record deploying Python apps to production.
• Strong backend design patterns and performance focus.
• Experience with background processing and concurrent work.
• Familiarity with LLM integration and context window optimization.
• Ability to debug AI behavior and implement fixes.
• Solid testing discipline for backend and AI components.
• Experience with Celery or similar libraries and monitoring.

Responsibilities

• Design, develop, and deploy production-grade AI-powered backend systems.
• Integrate LLMs and ML models into scalable architectures.
• Optimize vector databases for RAG pipelines and ML queries.
• Write clean Python code with best practices.
• Balance LLM calls with traditional ML for performance.
• Debug cross-layer issues across backend, AI, and UI.
• Conduct thorough dev testing before QA handoff.
• Collaborate with product, backend, and frontend engineers.

Skills

Python backend

FastAPI/Flask

Celery

Distributed systems

Performance tuning

LLM integration

Prompt engineering

Debug AI behavior

Testing discipline

Education

Masters degree

Tools

Celery

Docker

Kubernetes

Nginx

FastAPI

Git

Job description

About Us

We’re a fast-growing product company integrating cutting-edge AI capabilities into our core offering to stay competitive and deliver exceptional value to customers. Our AI work spans task-specific ML models, large language model (LLM) integration, and agentic systems that orchestrate multiple tools to produce end-user results.

We run a Python-based backend (FastAPI + Gunicorn + Nginx) with heavy background job processing using Celery. We’re looking for a senior-level AI Engineer who is equally strong in backend engineering and applied AI — capable of building production-grade systems that are fast, reliable, and maintainable.

What You’ll Do

• - Design, develop, and deploy production-grade AI-powered backend systems.
• - Integrate LLMs and traditional ML models into performant, scalable architectures.
• - Integrate and optimize vector databases for retrieval-augmented generation (RAG) pipelines and other traditional ML queries.
• - Write clean, well-structured, and testable Python code following best practices.
• - Capable of thinking about performance and ensuring optimal decision making to reduce latency.
• - Build hybrid architectures that balance LLM calls with traditional ML.
• - Debug complex, cross-layer issues spanning backend, AI inference, and UI integration.
• - Conduct thorough dev testing before QA handoff to ensure production reliability.
• - Collaborate with product, backend, and frontend engineers to deliver cohesive solutions.

Must-Have Skills & Experience

• - 3–5+ years professional backend engineering experience in Python, FastAPI or Flask, and background processing.
• - Masters Degree in related field
• - Proven record of deploying Python applications to production (not just scripts or academic work).
• - Strong grasp of software design patterns
• - Strong understanding of backend performance, parallel processing in background jobs and multi-threading
• - Proficiency in performance tuning specially for heavy AI models
• - Applied machine learning experience — training, evaluating, and maintaining small task-specific models.
• - Familiarity with LLM integration, prompt engineering, and context window optimization.
• - Proven ability to debug AI behavior, identify root causes, and make targeted fixes.
• - Strong testing discipline for both backend and AI components.
• - Experience with background processing with Celery or other major libraries
• - Experience with monitoring APIs and background processing
• - Experience with ensuring visibility and error reporting.
• - Nice to have: experience with Docker, understanding of CI/D, deployment automation and Kubernetes

Who Will Succeed in This Role

• - Independent problem solver — you can debug without constant supervision.
• - Production mindset — you understand that reliability, scalability, and maintainability matter as much as accuracy.
• - System thinker — you see backend, AI, and UI as a connected whole.

Why Join Us

• - Direct impact on the company’s competitive edge.
• - Small, fast-moving team with high autonomy.
• - Work on practical, real-world AI applications — not just research.
• - Opportunity to shape our AI architecture and best practices from the ground up.
• - Benefits Package, with time off and Holiday pay

If you’re a backend-first AI engineer who thrives in shipping production-ready systems and knows how to make AI practical, fast, and reliable — we’d love to talk.