Senior AI/ML Engineer (Autonomous Agents, RAG)

Location: Remote (Poland, Germany, UK)

Type: Full-time

Experience: 6+ years Engineering / 2+ years AI-focused
 

Language: English B2
+

Role Overview

We are seeking a highly skilled AI/ML Engineer to join our dynamic team. In this role, you will be the primary architect for autonomous AI agents, designing complex multi-agent workflows and implementing state-of-the-art RAG pipelines to solve real-world business challenges.

Key Responsibilities

• Autonomous Agents: Develop autonomous AI agents and multi-agent workflows leveraging tool calling and advanced reasoning.
• LLM Systems: Build and optimize LLM-based systems, including prompt engineering, fine-tuning, and performance evaluation.
• RAG Pipelines: Design and implement Retrieval-Augmented Generation (RAG) pipelines integrating external knowledge sources and vector databases.
• Production Optimization: Optimize models and agents for production environments with a focus on latency, throughput, and cost-efficiency.
• Innovation: Stay current with the evolving LLM/NLP landscape and apply state-of-the-art techniques to production use cases.
   

Technical Requirements

• Experience: A minimum of 2 years of AI-focused experience and 6+ years of overall engineering background.
• Programming: Strong proficiency in Node.js (TypeScript) and Python.
• LLM Ecosystem: Practical experience in fine-tuning, deploying, and optimizing LLMs (OpenAI, Llama, Claude, Gemini, Grok).
• NLP Expertise: Deep knowledge of prompt engineering, embeddings, and semantic search.
• Vector Search: Experience with RAG techniques and vector databases (Pinecone, Weaviate, Faiss, or pgvector).
• Orchestration: Experience with LLM orchestration frameworks (LangGraph, LlamaIndex, etc.) and multi-agent architectures.
   

Nice to Have

• Evaluation: Experience with Promptfoo, LangTest, or other tools for automated LLM evaluation and regression tracking.
• Deep Learning: Experience with transformer-based models and frameworks (Hugging Face, PyTorch, TensorFlow).
• Responsible AI: Experience in deploying safety guardrails and mitigating bias in AI systems.
• Open Source: Contributions to open-source ML projects or relevant publications.