Remote AI Engineer: Production LLM Apps & Agents

aptendo; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Aptendo is expanding its AI Engineering practice to deliver robust, production-grade LLM applications for international enterprise clients. You will join a cross-functional team of data scientists, software engineers, and product managers to design, deploy, and operate RAG systems, copilots, and agentic automation at scale.

As an AI Engineer, you’ll build retrieval pipelines, implement observability, and ensure secure API integrations across cloud providers while optimizing costs and latency.

Qualifications

• 4+ years in software or ML engineering.
• 2+ years building LLM/GenAI applications.
• At least one GenAI solution you took to production.
• Experience evaluating and debugging LLM systems.
• Strong engineering habits: testing, monitoring, error handling, and clean APIs.
• Clear communication with both technical and business stakeholders.

Responsibilities

• Build and ship LLM-powered applications: RAG systems, AI copilots, and agentic workflows with tool use.
• Design retrieval pipelines (chunking, embeddings, hybrid search, reranking) and measure their quality.
• Set up evaluation frameworks and LLM observability, covering accuracy, hallucinations, latency, and cost.
• Integrate AI services into enterprise systems through secure APIs and backend services.
• Optimize for production by working on caching, model routing, prompt and context design, and token cost.
• Apply guardrails, access control, and protection against prompt injection and data leakage.
• Deploy and operate solutions on AWS, Azure, or GCP with CI/CD and monitoring in place.
• Use classical ML (classification, prediction, NLP) where it is the better tool than an LLM.

Skills

Python

FastAPI

LLM/GenAI development

Distributed systems

Model evaluation

Tools

PyTorch

scikit-learn

LangChain

LlamaIndex

OpenAI API

Pinecone

Docker

CI/CD

AWS

Job description

Aptendo is expanding its AI Engineering practice to deliver robust, production-grade LLM applications for international enterprise clients. You will join a cross-functional team of data scientists, software engineers, and product managers to design, deploy, and operate RAG systems, copilots, and agentic automation at scale.

As an AI Engineer, you’ll build retrieval pipelines, implement observability, and ensure secure API integrations across cloud providers while optimizing costs and latency.