Apply Now

Full Stack Developers - LLM API integration

Santa Clara, CA, US • Posted 3 hours ago • Updated 3 hours ago

Contract Independent

Contract W2

1 Year

No Travel Required

On-site

$75 - $80/hr

MASH Pro Tech

Fitment

Dice Job Match Score™

⭐ Evaluating experience...

Job Details

Skills

Google Cloud Platform
Microsoft Azure
Microsoft Certified Professional
Node.js
JavaScript
LangChain
Machine Learning (ML)
Management
Dashboard
Docker
GitHub
Good Clinical Practice
JSON
Accessibility
Amazon Web Services
RESTful
React.js
Real-time
Artificial Intelligence
NIM
PostgreSQL
Python
Responsive Design
Routing
SDK
Streaming
TypeScript
UI
Value Engineering
WebSocket
Wireframe
Workflow
API

Summary

Full Stack Developer:

React + TypeScript — the entire frontend stack. No exceptions.
Multi-tenancy / row-level security / app scaling — Has designed and operated a multi-tenant application at scale — where tenant isolation and scaling are production requirements.
LLM API integration — must have shipped something that calls an LLM, handles streaming responses, and deals with tool use / function calling. A generic full-stack engineer who has never worked with AI APIs will have a steep ramp on every single product in the portfolio.
Streaming UI patterns (SSE, WebSockets) — all the agents stream. If they''ve never built a chat/streaming interface, the first few months are spent learning the basics.
REST API design + async backend (FastAPI or similar Python backend is a plus given the existing stack)
Own the full UI lifecycle from wireframe to production: accessibility, responsive design, performance, and iterative refinement based on user feedback
Implement token-level SSE (Server-Sent Events) streaming for real-time AI response rendering — ensuring low-latency, high-quality conversational experiences
Design and build front-end applications, dashboards, and learner-facing experiences for new AI agents using React and Next.js
Build the application logic that orchestrates multi-step agent workflows — routing inputs, managing conversation state, and handling tool-use sequences
Collaborate with AI/ML engineers to integrate structured JSON generation outputs into typed rendering pipelines

Frontend:  React · Next.js · TypeScript · Vercel AI SDK ·
Backend:  Node.js · Python · REST · SSE streaming · GraphQL
AI/ML:  NVIDIA NIM · Nemotron · RAG pipelines · structured JSON generation
Infra:  Vercel · AWS/Google Cloud Platform/Azure · Docker · GitHub Actions
Data:  PostgreSQL · pgvector · Redis

Nice to have: Lammaindex, Langchain experience, MCP server design, Vercel AI SDK or similar.

Hard disqualifier: Pure frontend engineer with no backend depth, or a backend engineer with no modern React experience. This role must be genuinely full-stack.

Employers have access to artificial intelligence language tools (“AI”) that help generate and enhance job descriptions and AI may have been used to create this description. The position description has been reviewed for accuracy and Dice believes it to correctly reflect the job opportunity.

Dice Id: 91166674
Position Id: 8983427
Posted 3 hours ago

Company Info

About MASH Pro Tech

Welcome to MASH Pro Tech, where innovation meets excellence. We are a leading technology solutions provider dedicated to transforming businesses through cutting-edge technology and unparalleled expertise. Our mission is to empower organizations with the tools and knowledge they need to thrive in the digital age.

Choosing MASH Pro Tech means partnering with a team that is passionate about technology and dedicated to your success. We take the time to understand your business and develop solutions that drive real results. With our extensive experience and commitment to excellence, you can trust us to deliver the best possible outcomes for your organization.

Go to company profile

Contact the job poster

Poojith Kiran

Recruiter @ MASH Pro Tech

View Profile

Create job alert

Never miss an opportunity! Create an alert based on the job you applied for.

Similar Jobs

LLM Application Development Engineer

Santa Clara, California

•

Today

AI Application Engineer - LLM Application DevelopmentSanta Clara - 5 days OnsiteNVIDIA-Specific StackNVIDIA NIM deployment, inference, API integration, model lifecycle Advanced Must-haveNeMo framework model configuration, inference optimization Proficient Must-haveNeMoGuardrails rails configuration, content safety models, jailbreak detection, topical control Advanced Must-haveNVIDIA Riva ASR / TTS integration in application layer Proficient Must-haveNVIDIA NIM models llama-3.1-nemog

Easy Apply

Contract

80 - 85

Search all similar jobs