Full Stack Engineer

ZRG Careers

New York (NY)

Hybrid

USD 140,000 - 180,000

Full time

8 hours ago

Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Comprehensive Benefits

Job summary

ZRG Careers is seeking a Senior Full-Stack Engineer in a hybrid capacity with minimum three days onsite in New York City. You will work across frontend, backend, and AI systems, partnering with Product, Design, Data, and Content teams to build AI-assisted experiences.

The ideal candidate has 7+ years of software engineering experience across frontend and backend, with strong TypeScript/React/Next.js and Python/Django mastery.

Qualifications

7+ years of professional software engineering experience across frontend and backend.
Advanced experience with TypeScript, React, and Next.js.
Strong experience with Python and Django.
Experience designing and building RESTful APIs.
Experience with relational databases such as PostgreSQL or MySQL.
Experience with vector databases such as Pinecone.
Experience in AWS, GCP, or similar cloud environments.
Experience monitoring production services and owning service health.
Demonstrated experience leading technical projects.
Ability to deliver incremental releases via feature flags and staged rollouts.
Strong focus on data-driven problem solving and customer insight.
Excellent written and verbal communication; collaborative mindset.

Responsibilities

Collaborate with cross-functional teams to design, develop, and maintain features across the full technology stack.
Build high-quality frontend applications using Next.js, React, and TypeScript, including streaming chat interfaces.
Design, develop, and maintain backend services and APIs using Python and Django.
Work with databases like PostgreSQL, Redis, Pinecone, and Contentful.
Monitor AI performance metrics and system latency; improve TTFT and reliability.
Deliver accessible and localized user experiences across platforms.
Own projects end-to-end from architecture to deployment and monitoring.
Mentor junior engineers and contribute to engineering best practices.

Skills

TypeScript

React

Next.js

Python

Django

RESTful APIs

PostgreSQL

MySQL

AWS

GCP

Datadog

Sentry

LangSmith

Pinecone

Contentful

LangChain

LangGraph

Tools

Datadog

Sentry

LangSmith

Pinecone

Contentful

LangChain

LangGraph

PostgreSQL

MySQL

Job description

About the Opportunity:

This is a hybrid role requiring a minimum of three (3) days per week onsite in New York City, with a preference for Monday, Tuesday, and Thursday.

We're looking for a Senior Full-Stack Engineer to join a collaborative engineering team and work across frontend, backend, and AI systems. You'll partner closely with Product, Design, Data, and Content teams to build and evolve digital platforms and AI-assisted experiences.

The ideal candidate is comfortable working across the stack—from React and Next.js on the frontend to Python and Django on the backend—and has demonstrated experience building LLM-powered products. You'll contribute to a growing portfolio of AI tools, including conversational assistants and emerging multimodal experiences.

What You'll Do

Collaborate with cross-functional teams (Product, Design, Data, and Content) to design, develop, and maintain features across the full technology stack.

Build high-quality, accessible frontend applications using Next.js, React, and TypeScript, including stateful, streaming chat interfaces and multimodal experiences (voice, text-to-speech, speech-to-text).

Design, develop, and maintain backend services and APIs using Python, Django, and SQL, integrating with technologies such as PostgreSQL, Redis, Pinecone, and Contentful.

Monitor and improve AI performance metrics, including system latency and time-to-first-token (TTFT).

Develop accessible and localized user experiences.

Own projects throughout the entire software development lifecycle—from architecture and planning through deployment and monitoring.

Deliver incremental releases using feature flags, A/B testing, and progressive rollouts.

Analyze user feedback, support tickets, and product analytics to continuously improve the user experience.

Utilize monitoring and observability tools such as Datadog, Sentry, and LangSmith to maintain production system health.

Collaborate with both internal teams and external development partners on solution design, integrations, and code reviews.

Mentor junior engineers and contribute to engineering best practices.

Stay current on emerging technologies and recommend improvements to development processes and product capabilities.

Required Qualifications

7+ years of professional software engineering experience with significant expertise in both frontend and backend development.

Advanced experience with TypeScript, React, and Next.js, including building stateful and streaming user interfaces.

Strong experience with Python and Django (or equivalent backend frameworks).

Experience designing and building RESTful APIs.

Experience working with relational databases such as PostgreSQL or MySQL.

Experience with vector databases such as Pinecone.

Experience working in cloud environments such as AWS, Google Cloud Platform, or similar.

Experience monitoring production services and owning service health.

Demonstrated experience leading technical projects.

Ability to break complex initiatives into incremental, user-focused releases using feature flags, staged rollouts, and experimentation platforms (such as Statsig).

Strong focus on solving real user problems through data, analytics, and customer feedback.

Excellent written and verbal communication skills.

Collaborative mindset with a passion for mentoring and continuous improvement.

Familiarity with distributed tracing, log analytics, and modern observability tools.

Preferred Qualifications

Experience building production-grade LLM applications using technologies such as LangChain, LangGraph, LangSmith, Model Context Protocol (MCP), multi-agent routing, memory, and personalization.

Experience implementing prompt engineering, evaluation frameworks, guardrails, fallbacks, and mitigation strategies for AI reliability.

Experience with Retrieval-Augmented Generation (RAG) architectures and vector databases including Pinecone, Weaviate, or pgvector.

Experience building real-time, multimodal AI applications using streaming text, voice, text-to-speech, speech-to-text, WebRTC, Web Audio, and real-time OpenAI APIs.

Trust, Safety & Compliance