Offer summary

Qualifications:

Strong understanding of LLM-based application architectures and AI software development trends., Experience with backend systems (Java, Python) and frontend applications (React, TypeScript)., Familiarity with agentic system architectures and best practices for LLM safety and performance., Bonus: Experience with orchestration platforms or designing internal LLM tooling..

Key responsabilities:

Build and maintain full stack features integrating LLM-based workflows.

Design and implement robust architectures for LLM-based applications with a focus on multi-modal use cases.

Collaborate with cross-functional teams to prototype and productionize AI-driven features.

Ensure the system is scalable, testable, and well-documented.

Job description

Job Title: Full Stack Engineer - AI Applications
Compensation Starts at $4,200/month

About Assembly Industries:
Talent is distributed but Opportunities are not - Assembly Industries is breaking that pattern by building an AI enabled talent platform that connects top-tier, highly skilled global professionals with innovative companies across the US. As a fast-growing startup, we are laser-focused on impactful growth, agile strategies, and exceptional results.

Role Overview:
We are seeking a Full Stack Engineer focused on AI applications to join our team in building cutting-edge, intelligent software experiences. This role requires someone with a strong product mindset and deep technical expertise across both frontend and backend systems, with a particular focus on leveraging large language models (LLMs) and other foundational models to deliver real value.

Required Experience:

Strong understanding of LLM-based application architectures and current trends in AI software development
Experience using foundational models (OpenAI, Claude, Gemini, etc.) across multiple modalities
Comfortable building and debugging both backend systems (Java, Python) and frontend applications (React, TypeScript)
Familiarity with agentic system architectures, including how to manage memory, state, and planning within LLM-powered agents
Understanding of best practices for LLM safety, prompting, and performance
Bonus: Experience with orchestration platforms or designing internal LLM tooling and capabilities

Required Skills:

Build and maintain full stack features using Java (backend APIs) and React/TypeScript (frontend), with integration into LLM-based workflows using Python
Design and implement robust architectures for LLM-based applications, with an emphasis on retrieval-augmented generation (RAG), agentic workflows, and multi-modal use cases (text, audio, video)
Integrate and experiment with foundational models for chat, audio, video, and other modalities
Work with model abstraction and chaining libraries (e.g., LangChain or similar frameworks)
Implement and optimize RAG pipelines including document loaders, chunking strategies, embedding models, and vector database integrations (e.g., Pinecone, Weaviate, FAISS)
Contribute to the design and implementation of agentic applications, including decision trees, stateful interactions, and orchestration strategies
Collaborate cross-functionally with product, design, and other engineering teams to prototype and productionize AI-driven features
Ensure the system is scalable, testable, and well-documented.