AI LLM Engineer (Only LATAM)

QAPOT; Polska; Hybrid; PLN 180,000 - 240,000; Full time

Job summary

QAPOT is seeking an experienced AI LLM Engineer to design and build scalable solutions powered by large language models. You will integrate AI into production systems across backend services, APIs, and data pipelines, collaborating with product and engineering teams to ship features quickly.

You should be proficient with OpenAI and open-source LLMs, Python, prompt engineering, vector databases, and cloud platforms (AWS/GCP/Azure).

Qualifications

• Strong experience with LLMs (OpenAI and open-source models).
• Proficiency in Python and API/backend development.
• Experience with prompt engineering and LLM evaluation.
• Familiarity with vector databases (Pinecone, Weaviate, FAISS).
• Experience building scalable systems on AWS/GCP/Azure.
• Understanding of APIs and backend architecture.

Responsibilities

• Design, develop, and deploy LLM-powered features.
• Build prompt pipelines and evaluation frameworks.
• Fine-tune models and optimize cost, latency, and performance.
• Work with embeddings, vector DBs, and retrieval (RAG).
• Integrate AI capabilities into production systems and APIs.
• Collaborate with product and engineering teams to ship features quickly.

Skills

LLMs

Python

Prompt engineering

Vector databases

APIs & backend

Cloud platforms

Tools

Pinecone

Weaviate

FAISS

LangChain

LlamaIndex

Job description

Are you ready to take the next step in your career? Our staffingservices company is here to help you find the perfect job that matchesyour skills, experience, and career aspirations. We work with topcompanies across various industries, offering exciting opportunitiesthat can lead to long-term success.

Job Description

This is a remote position.

We are looking for an experienced AI LLM Engineer to design and build scalable solutions powered by large language models. You will play a key role in integrating AI into real-world applications, working across backend systems, APIs, and data pipelines.

What You’ll Do

• Design, develop, and deploy LLM-powered features
  
• Build and optimize prompt pipelines and evaluation frameworks
  
• Fine-tune models and improve performance, latency, and cost
  
• Work with embeddings, vector databases, and retrieval systems (RAG)
  
• Integrate AI capabilities into production systems and APIs
  
• Collaborate with product and engineering teams to ship features fast
  

Requirements

Requirements

• Strong experience with LLMs (OpenAI, open-source models, etc.)
  
• Proficiency in Python
  
• Experience with prompt engineering and LLM evaluation techniques
  
• Familiarity with vector databases (Pinecone, Weaviate, FAISS, etc.)
  
• Experience building scalable systems (AWS, GCP, or Azure)
  
• Solid understanding of APIs and backend architecture
  

Nice to Have

• Experience with fine-tuning and model optimization
  
• Knowledge of LangChain, LlamaIndex, or similar frameworks
  
• Background in NLP or machine learning
  
• Experience with streaming, real-time systems, or agents
  
• Competitive compensation
  
• Opportunity to work on cutting-edge AI products