Home
Jobs
Saved
Resumes
AI Engineer at Distro | JobVerse
JobVerse
Home
Jobs
Recruiters
Companies
Pricing
Blog
Jobs
/
AI Engineer
Distro
Remote
Website
LinkedIn
AI Engineer
Guatemala
Full Time
2 hours ago
$35 - $50 USD
H1B Sponsor
Apply Now
Key skills
AWS
Azure
Cloud
Google Cloud Platform
Python
AI
LLM
OpenAI
Anthropic
RAG
Vector Database
Pinecone
Weaviate
FastAPI
GCP
Google Cloud
Caching
About this role
Role Overview
Design and implement LLM-powered application workflows
Architect prompt orchestration, tool calling, and multi-step reasoning pipelines
Define model selection strategy (OpenAI, Anthropic, open-source models, etc.)
Implement streaming responses for mobile and web clients
Optimize token usage and latency for production environments
Build fallback and resilience strategies across model providers
Architect retrieval-augmented generation pipelines
Design vector database schema and embedding workflows
Implement chunking, metadata tagging, and indexing strategies
Optimize semantic search relevance
Collaborate with backend architects to integrate AI services into APIs
Design asynchronous processing pipelines for AI workflows
Implement caching strategies for inference results
Architect evaluation and monitoring frameworks for LLM output quality
Build guardrails, moderation layers, and output validation
Define evaluation metrics for response quality
Implement automated testing for LLM outputs
Analyze hallucination patterns and mitigation techniques
Monitor drift, cost, and performance metrics
Continuously improve prompt and architecture strategies
Implement data privacy safeguards
Ensure compliance with enterprise security requirements
Design safe handling of user-generated content
Implement access control and audit logging
Guide LLM architecture decisions across the platform
Mentor engineers working on AI-related components
Evaluate emerging AI tools and frameworks
Requirements
5–8+ years in software engineering with at least 2+ years focused on LLM systems
Production experience integrating LLM APIs
Strong experience with: Python (FastAPI preferred)
Vector databases (pgvector, Pinecone, Weaviate, etc.)
Embeddings and semantic search
Prompt engineering and tool invocation workflows
Experience building RAG systems in production
Experience optimizing latency and inference costs
Strong understanding of tokenization, context windows, and model limitations
Experience deploying AI services in cloud environments (AWS, GCP, Azure)
Tech Stack
AWS
Azure
Cloud
Google Cloud Platform
Python
Apply Now
Home
Jobs
Saved
Resumes