Senior Python AI Engineer (green building)

About the project

Project for a client that promotes green building design.

Our expectations

Python Expert: 5+ years of commercial experience writing production-quality code. You should be proficient in building scalable services, APIs (FastAPI, Flask, Django), and comprehensive test suites (pytest).

Clean Code & Architecture: A strong advocate for clean code principles and the ability to build modular, maintainable software architectures.

Hands-on experience with LangChain or other advanced patterns using LangGraph, LangSmith, or LlamaIndex.

Agentic Workflows: Proven ability to build autonomous AI agents involving tool-calling, function-calling, and complex multi-step reasoning.

RAG & Vector Search: Practical expertise in implementing Retrieval-Augmented Generation (RAG) using vector databases (e.g., Pinecone, Weaviate, Milvus, or Pgvector) and optimizing embedding models.

Prompt Engineering Expert-level skill in prompt design, structured outputs (JSON/Pydantic/Instructor).

The '

Evals' Mindset: You understand that 'it works on my machine' isn't enough. You have experience building evaluation frameworks to measure relevance, consistency, latency, cost, and user trust.

End-to-End Delivery: A track record of taking AI-powered applications from initial ideation and prototyping through to full-scale production deployment.

Data Literacy: Solid understanding of how data quality, freshness, and structure impact model behavior. Experience with building data pipelines for AI consumption.

Experience with at least one major cloud platform (Azure, AWS, or GCP), specifically utilizing their managed AI/ML services (e.g., Azure OpenAI, AWS Bedrock).

Skills in integrating LLMs into existing product ecosystems via microservices or workflow engines.

High-proficiency in written and spoken English (min. B2+ level).

Welcome Skills'

Getting Things Done' Attitude: A proactive, problem-solving mindset suited for a fast-paced, client-facing environment.

Product-First Engineering Mindset: Ownership of the AI lifecycle - from initial ideation and architectural design to production deployment. This includes proactively partnering with stakeholders to refine requirements, identifying the highest-ROI AI patterns, and pivoting quickly based on real-world performance data and user feedback.

Stakeholder Communication: The ability to translate complex technical AI concepts into clear business solutions for non-technical stakeholders.