Gen AI Engineer – AI/LLM Backend Focus (Contract to Hire, Remote – U.S. Eastern Time Zone)

Informulate; United States; Remote; USD 80,000 - 100,000; Full time

Job summary

Join an innovative company as a Gen AI Engineer, where you'll leverage your expertise in large language models to design cutting-edge backend systems that power intelligent applications. This fully remote role offers the flexibility to work with a tight-knit team on exciting AI-driven solutions. You'll be at the forefront of developing scalable conversational agents, automating workflows, and creating semi-autonomous systems. If you're passionate about AI and eager to make a lasting impact, this is the perfect opportunity for you!

Qualifications

• Deep expertise in LLM architectures and frameworks for AI applications.
• Experience with agentic workflows and retrieval-augmented generation techniques.
• Proficient in Python and data modeling using Pydantic.

Responsibilities

• Design and implement AI/LLM backend systems for intelligent applications.
• Architect robust backends and manage high-performance knowledge bases.
• Collaborate on diverse AI projects including chatbots and automation tools.

Skills

LLM Framework Expertise

Agentic Workflows

Retrieval-Augmented Generation (RAG)

Knowledge Bases & Vector Databases

Python & Pydantic

Model Fine-tuning & Evaluation

MCP Protocol

AWS Bedrock

Voice-Enabled AI

Model Providers & Private LLMs

React

Node.js

TypeScript

Tools

LangChain

LangGraph

Crew AI

Pinecone

Weaviate

Faiss

Annoy

Docker

AWS

OpenAI’s Voice API

Job description

Gen AI Engineer – AI/LLM Backend Focus (Contract to Hire, Remote – U.S. Eastern Time Zone)

This range is provided by Informulate. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.

Base pay range

$60.00/hr - $70.00/hr

Application Details

Direct message the job poster from Informulate

Role Overview

Informulate is seeking a Gen AI Engineer with deep expertise in large language model (LLM) architectures to join our team. In this role, you will design and implement cutting-edge AI/LLM backend systems that power intelligent applications, including chatbots and semi-autonomous agents. Responsibilities include architecting robust backends, orchestrating agentic workflows, retrieval-augmented generation (RAG) pipelines, and managing high-performance knowledge bases.

This is a fully remote position (U.S. only) with flexible hours aligned with Eastern Time. We welcome both part-time and full-time contractors to collaborate virtually on AI-driven solutions that innovate and scale.

Key Requirements

• LLM Framework Expertise: Experience with frameworks like LangChain, LangGraph, Crew AI, or similar for building conversational and agent-driven applications.
• Agentic Workflows: Knowledge of agent types and paradigms such as ReAct (reason-act), planning, and reflective agents, with hands-on experience implementing multi-step AI workflows.
• Retrieval‑Augmented Generation (RAG): Advanced understanding of RAG techniques, including graph RAG, hybrid RAG, and agentic RAG methods to augment LLMs with external knowledge.
• Knowledge Bases & Vector Databases: Experience building scalable vector-based knowledge bases (e.g., Pinecone, Weaviate) and optimizing vector searches with algorithms like HNSW, IVF, PQ, and libraries such as Faiss, Annoy.
• Python & Pydantic: Proficiency in Python, especially using Pydantic for data validation and modeling.
• Model Fine‑tuning & Evaluation: Hands-on experience fine-tuning LLMs and using evaluation frameworks like LangSmith.
• MCP Protocol: Understanding of the Model Context Protocol (MCP) for dynamic context management.
• AWS Bedrock: Familiarity with AWS Bedrock services or the ability to learn quickly.
• Voice‑Enabled AI: Experience integrating voice AI technologies, such as OpenAI’s Voice API.
• Model Providers & Private LLMs: Experience working with APIs from providers like OpenAI, Anthropic, Google, and hosting private LLM instances.
• Front-end experience with React and backend with Node.js and TypeScript.

Preferred Qualifications

• Cloud Deployment: Experience deploying LLM applications on cloud platforms (AWS preferred), including CI/CD, Docker, and security best practices.
• Prompt Engineering: Mastery in designing and optimizing prompts systematically.
• AI‑Native Architecture Design: Ability to create modular, scalable AI-first systems, leveraging serverless and pipeline patterns.

Application Domains

Work on diverse AI projects such as:

• LLM‑Powered Chatbots: Building scalable conversational agents for support and virtual assistance.
• Workflow Automation: Creating intelligent automation tools for business processes.
• Semi‑Autonomous Agents: Developing systems of collaborative agents for complex tasks.

Company & Culture

Informulate (informulate.com, informulate.ai) is a U.S.-based software consulting firm specializing in innovation, custom development, and AI-driven products. Founded in 2006, we blend Lean Startup, Agile, and Design Thinking to deliver measurable impact. Our AI division, Informulate.AI, focuses on generative AI research and solutions.

As a remote-first company with a tight-knit culture, we uphold core values:

• Empathy: Understanding and advocating for user and client needs.
• Quality: Striving for excellence in every aspect.
• Integrity: Maintaining trust and accountability.
• Impact: Creating lasting business value.
• Simplicity: Designing clear and elegant solutions.
• Responsiveness: Acting swiftly and adapting to challenges.

How to Apply

If you’re passionate about AI and meet the above requirements, we want to hear from you! Send your resume and relevant project links (GitHub, portfolio, LinkedIn) to [e-mail]. Include a brief introduction explaining why you’re a great fit for our Gen AI Engineer role.

We look forward to innovating together!