> Markdown version of [/jobs/ext/3975326-senior-backend-engineer](https://www.wearedevelopers.com/jobs/ext/3975326-senior-backend-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior Backend Engineer

- **Company:** Newfold Digital
- **Location:** Miami, FL, United States
- **Experience:** Expert
- **Contract:** Permanent contract
- **Skills:** A/B Testing, Application Programming Interfaces (APIs), Artificial Intelligence, Business Logic, Code Generation, Continuous Integration, Customer Data Management, Relational Databases, Dependency Injection, Python (Programming Language), Query Optimization, OpenAI, SQLAlchemy, WebSocket, Network Routing, Scripting, Retrieval-Augmented Generation, Large Language Models, Multi-Agent Systems, Generative AI, Backend, Fastapi, Pgvector, Google Gemini, Restful APIs, Semantic Kernel, Dynatrace, ChromaDB
- **Published:** October 27, 2026
- **Apply:** https://www.careerbuilder.com/job-details/senior-backend-engineer-miami-fl--f41348ee-7084-4619-a3ff-71d0bf11dda7

## About the Role

Small Business, Business Growth, Artificial Intelligence (AI), SLICE (Simulation Language with Integrated Circuit Emphasis), Application Programming Interface (API), REST (Representational State Transfer), Dependency Injection, Python Programming/Scripting Language, Network Routing, A/B Testing, * 5+ years building production backend systems in Python, with real async I/O experience

 * Hands-on experience designing and scaling REST or async APIs, including dependency injection and clean service architecture
 * Practical experience integrating LLM APIs (OpenAI, Gemini, or similar) and building AI-readiness into backend systems from the ground up
 * Real experience with vector databases and RAG-style retrieval architectures, not just reading about them
 * Strong relational database skills: schema design, query optimization, and migration discipline
 * AI-augmented delivery: you use AI across the delivery lifecycle, not just code generation, and can say which models suit which problems and where you don't use them. You review AI-generated code knowing its failure modes, and you have set the guardrails others work inside - review expectations for generated code, provenance and licensing checks, and clear boundaries for what customer data enters a prompt and what a security or compliance review will ask for.
 * End-to-end CI/CD ownership, from build and test through packaging and deployment
 * A self-starting, go-getter mindset: comfortable with ambiguity, fast iteration, and owning a problem until it's actually solved
 * Bonus: experience with multi-agent orchestration frameworks (Semantic Kernel, LangChain, or similar) and LLM cost/observability tooling

## Description

* Design and scale async REST/WebSocket APIs in Python (FastAPI or similar), using dependency injection, type hints, and clean, vertical-slice architecture
 * Implement multi-agent workflows (sequential, concurrent, and handoff patterns) to route work among specialized LLM agents
 * Integrate multiple LLM providers behind a provider-agnostic layer, enabling A/B testing and cost-aware routing rather than hard-coding a single vendor
 * Build and maintain Retrieval-Augmented Generation (RAG) pipelines against vector stores such as pgvector, Chroma, or a managed vector search service
 * Design schemas and evolve data models (SQLAlchemy/SQLModel-style ORM plus migrations) that support both traditional application logic and AI-driven features
 * Instrument services with structured logs, distributed tracing, and cost/latency metrics, holding a real bar for p95 response time under production load
 * Maintain end-to-end CI/CD ownership, lint, type-check, test, package, and deploy, so releases are boring and safe
 * Champion AI across the delivery lifecycle, not just code generation, and set the guardrails the team works inside: how generated code gets reviewed, how provenance and licensing are checked, and what customer data may enter a prompt
 * Move ideas from concept to production fast, with real ownership over architecture and outcomes, not just tickets