Must have

• Python

• ML

• AI

• NLP

• Pandas

• NumPy

• scikit-learn

• TensorFlow

• PyTorch

• API

• English

Nice to have

• Vector Stores

• Elasticsearch

• AI Assistants

• LLMs

• Prompt engineering

• Data-heavy search

• FTS engines

• Chemical Data

Requirements description

• 2–4 years of experience in Python development (ideally in a data-focused context)
• Hands-on experience with ML, data science or NLP projects
• Familiarity with tools such as Pandas, NumPy, Scikit-learn, TensorFlow or PyTorch
• Experience working with APIs and integrating them into backend systems
• Solid understanding of clean code, version control and testing practices
• Hands-on experience with vector stores or Elasticsearch is a plus

Nice to have

• Interest or prior exposure to AI assistants, LLMs, Langchain or prompt engineering
• Experience with data-heavy search systems or FTS engines
• Familiarity with chemical data would be a bonus, but is not required

Offer description

You will join a cross-functional team responsible for building and scaling an AI-powered search platform. The project involves large-scale data ingestion, cleaning, normalization, and integration of complex taxonomies into intelligent pipelines.

As a Python Engineer, you’ll be working directly with internal APIs, building robust pipelines, and supporting the AI platform’s growth and performance. You will also have the chance to work with emerging tools such as Langchain or vector databases.

Your responsibilities

1. Design and maintain robust data pipelines for structured/unstructured data
2. Collaborate with internal teams to integrate APIs and support search functionality
3. Clean, normalize, and structure large volumes of extracted data
4. Support the architecture of the AI platform with scalability and performance in mind
5. Stay on top of the latest developments in ML/NLP and contribute to improving the solution