Summary
✨ AI‑Generated
A product-focused AI engineering role developing production-grade intelligent applications. Responsibilities include building LLM pipelines, retrieval systems, backend services, and automated workflows that connect AI capabilities with business applications.
Highlights
Build production AI applications, design advanced LLM workflows, and work on innovative automation solutions with flexible work options.
Description
Job Title: AI Engineer (Full-Stack / LLM Systems)
Location: Remote / Hybrid (New York Metro Area)
Employment Type: Full-time
About the Role
We are seeking an autonomous, product-minded AI Engineer to design, build, and deploy production-grade AI systems and intelligent workflow automation.
You will work directly on architecting scalable LLM pipelines, integrating vector search/RAG architectures, and connecting core AI models to practical enterprise and fintech software applications.
Key Responsibilities
Architect, build, and maintain production AI features using state-of-the-art LLMs, embeddings, and agentic workflows.Design robust RAG (Retrieval-Augmented Generation) pipelines, structured data extractors, and automated evaluation frameworks.Develop backend APIs, background job workers, and database schemas to support high-throughput AI features.Implement structured tool calling, orchestration logic, and webhooks to integrate AI capabilities with external services and databases.Optimize latency, token costs, context management, and reliability across model providers.
Qualifications & Requirements
3+ years of software engineering experience with strong proficiency in TypeScript / JavaScript or Python.Hands-on experience deploying LLM applications into production using frameworks like LangChain, LlamaIndex, or direct API integrations (Google Gemini, Anthropic, OpenAI).Solid experience with relational and vector databases (e.g., PostgreSQL / Supabase / pgvector, Pinecone, or Qdrant).Familiarity with modern deployment platforms and serverless architectures (e.g., Vercel, Next.js, Node.js).Strong understanding of data modeling, RESTful APIs, webhooks, and asynchronous workflows.High degree of ownership—comfortable translating open-ended business problems into resilient software.Preferred Experience
Background in financial software, automated data extraction, or enterprise workflow automation.Experience building autonomous web agents or complex tool-use chains.Familiarity with enterprise API ecosystems (Google Workspace APIs, CRMs, document processing).
How to Apply
Submit your resume, a link to your GitHub/portfolio, and 2–3 sentences highlighting an LLM system or complex automation you built and shipped to production.
Would you like to adjust the primary tech stack, seniority level, or compensation range before posting?
