Freelance LLM Engineer: AI Features & RAG Pipelines

Embedded Shishya; Kraków; On-site; PLN 123,984 - 179,088; Full time

Job summary

Embedded Shishya is building a network of LLM engineers to design, build, and integrate practical AI features into existing products. We welcome collaboration on a freelance basis—part-time or full-time depending on project needs.

We seek engineers with Python/Node.js/Ruby skills and hands-on experience integrating LLM APIs into production systems, plus expertise in RAG pipelines, embeddings, and vector search.

Qualifications

• Strong software engineering background in Python, Node.js or Ruby.
• Hands-on experience integrating LLM APIs into production systems (OpenAI, Anthropic or similar).
• Ability to design pragmatic AI solutions within existing architectures.
• Experience building RAG pipelines, embeddings and vector search.
• Understand cost, latency and reliability constraints of AI systems.
• Able to work independently with clients and set expectations.
• Background in big data or data pipelines is a big plus.
• English proficiency at B2/C1 level.

Responsibilities

• Add AI functionality into existing Python, Node.js and Ruby codebases.
• Build LLM-powered features: chat, summaries, classification, smart search, document Q&A.
• Design lightweight RAG pipelines using embeddings and vector search.
• Work with vector databases (pgvector, Pinecone, Qdrant).
• Implement safe, reliable LLM endpoints (OpenAI, Anthropic, Azure).
• Collaborate with clients to shape AI features and reduce manual effort.
• Advise clients when not to use AI, balancing latency, accuracy, and cost.

Skills

Python

Node.js

Ruby

LLM APIs

RAG pipelines

Embeddings

Vector search

Cost & latency

Independent work

Big data

English proficiency

Tools

pgvector

Pinecone

Qdrant

Job description

Embedded Shishya is building a network of LLM engineers to design, build, and integrate practical AI features into existing products. We welcome collaboration on a freelance basis—part-time or full-time depending on project needs.

We seek engineers with Python/Node.js/Ruby skills and hands-on experience integrating LLM APIs into production systems, plus expertise in RAG pipelines, embeddings, and vector search.