AI Developer

Location: Remote / Hybrid (Europe preferred)  
Reports to: CTO / Founders   

We are building an enterprise-grade AI assistant that helps organizations access and use their knowledge instantly and securely. Our system combines Retrieval-Augmented Generation (RAG), multi-tenant architecture, and secure cloud components to deliver accurate, context-aware answers inside complex corporate environments. 

We are now looking for a Machine Learning Engineer to join our core technical team and help us take our RAG stack to the next level. 

Your Responsibilities 

You will be responsible for designing, improving and maintaining the intelligence layer of our platform. This includes: 

RAG System Development 

• Improve our existing Python-based RAG pipelines (indexing, embedding, retrieval, reranking). 

• Implement vector database improvements (index updates, migrations, performance tuning). 

• Build robust document preprocessing & chunking pipelines for multi-format data. 

LLM Integration 

• Integrate and optimize prompts and workflows with OpenAI models. 

• Experiment with alternative LLMs (optional mode: BYOM/BYO-LLM). 

• Create guardrails, evaluation metrics, and automated quality tests. 

Infrastructure & Backend 

• Work closely with our AWS engineer to deploy, monitor, and scale the RAG services. 

• Implement secure data flows (S3, Lambda, Bedrock, IAM, API Gateway, etc.). 

• Help design multi-tenant and on-prem variations of the architecture. 

Search, Ranking & Embeddings 

• Evaluate new embedding models and retrieval strategies. 

• Improve semantic search quality and domain-specific relevance. 

• Research emerging techniques (rerankers, hybrid search, small local LLMs, etc.). 

Your Profile 

We are a startup, so we value practical engineering ability, ownership, and curiosity. 

Required 

• Solid Python skills (fast, clean, production code). 

• Hands-on experience with LLMs (OpenAI API or similar). 

• Extensive experience with RAG systems and vector databases (Qdrant, Pinecone, FAISS, etc.). 

• Familiarity with AWS (Lambda, S3, EC2, IAM, CloudWatch, API Gateway). 

• Experience with document extraction (OCR, PDF parsing, pipelines). 

• Good understanding of embeddings, semantic search, and prompt engineering. 

• Ability to take a feature from idea to deployed solution. 

What We Offer 

• Work directly with founders on a high-impact AI product. 

• A modern stack: Python, OpenAI, AWS, Qdrant, FastAPI (and you can shape it further). 

• High degree of autonomy and real influence on the product architecture. 

• Opportunity to work at the frontier of enterprise AI & RAG systems. 

• Flexible remote work 

How to apply: you may send your CV to @dasha_w25 (telegram)