Full-Stack Engineer

INFUSE•Georgia, GA

8d•Remote

About The Position

We are looking for an experienced Senior Fullstack / AI Engineer who will be responsible for end-to-end feature development — from building intelligent AI agents on the backend to visualizing them through intuitive user interfaces. This project features a bleeding-edge stack with no legacy code, focusing on complex distributed systems including RAG architecture, vector search, event streaming, and big data analytics. The tech stack includes Vue 3/React, TypeScript, Node.js (NestJS), Python (FastAPI), OpenAI, Anthropic, Google, PostgreSQL, ClickHouse, Qdrant, Kafka, Redis, and S3/MinIO.

Requirements

Senior level experience, 4–5+ years in product development.
Hands-on experience in LLM integration and data engineering.
Deep knowledge of Node.js, Worker threads, and the NestJS ecosystem (Dependency Injection, Modules, Guards, Interceptors, and Pipes).
Proficiency in TypeScript (Vue 3, NestJS).
Proven track record of backend development with Python.
Solid understanding of prompt engineering, LangChain chains, embeddings, and semantic search.
Understanding of differences between LLMs like Claude and GPT in production environments.
Practical experience with Qdrant (or similar vector databases), including indexing, similarity search, and vector tuning.
Experience working with distributed systems, message brokers (Kafka), and analytical databases (ClickHouse).
Clear understanding of when to query PostgreSQL, when to aggregate data in ClickHouse (OLAP vs. OLTP), and how vector indexes operate in Qdrant.
Experience with caching (Redis), object storage (S3/MinIO), containerization (Docker/Kubernetes), and the AWS ecosystem.
Strong analytical skills.
A product-driven mindset.
Ability to architect fault-tolerant systems.
Dedication to writing clean, maintainable code (SOLID, OOP/FP patterns).

Nice To Haves

Experience with React.

Responsibilities

Backend development with deep expertise in Node.js and/or Python (FastAPI), including asynchronous programming, RESTful APIs, and microservice architectures.
LLM integration, including production experience with LLM APIs (Anthropic, OpenAI or similar), covering structured outputs, retries, rate limits, streaming, fallbacks, and token economics.
Database management with strong PostgreSQL skills, including query optimization, execution plans, relational schema troubleshooting, and transaction isolation levels.
Debugging and observability using logs, metrics, distributed tracing (trace_id/request_id), and monitoring dashboards.
Testing with Jest, Supertest or PyTest, including robust regression tests and familiarity with evaluating non-deterministic (LLM) behavior.
AI-assisted development using agentic coding tools (Claude Code, Cursor or similar) as a normal working method, including verification of AI output.
Utilizing LLM observability and evaluation tooling (Langfuse, prompt/trace platforms, eval frameworks).
Working with Docker and standard CI/CD pipelines.
Implementing queue systems or event-driven architectures (Kafka, RabbitMQ).
Ensuring security hygiene, including dependency vulnerability triage and secrets management.
Performing analytical, systematic debugging of unfamiliar codebases.
Applying systems thinking to understand the impact of changes on the broader ecosystem.
Taking full ownership from triage to production verification and post-mortem.
Communicating root causes clearly to stakeholders.
Working within an Agile (Scrum/Kanban) framework using Jira and Confluence.