Senior Python Backend Architect for AI & LLM Platforms

Intellectsoft; España; On-site; EUR 90,000 - 130,000; Full time

Job summary

Intellectsoft seeks an experienced ML/backend engineer to build scalable ML platforms and backend systems in Spain. You will design and deploy APIs with FastAPI, implement MLOps for model KPI tracking, drift detection, and feedback loops, and orchestrate LLM workflows with LangChain.

You will integrate Azure OpenAI (GPT-4) and other providers, ensure async, DI patterns, and multi-tenant architectures while staying current on GenAI trends. Strong Python/CV/NLP background required.

Qualifications

• Bachelor's or Master's degree in Computer Science or related field.
• 7+ years of Python development experience.
• 2+ years of hands-on ML and production LLM systems.
• Experience building backend APIs with FastAPI and SQLAlchemy.
• Experience with DI, interfaces, and AB classes.
• Familiarity with vector DBs and hybrid search (Pinecone/Weaviate/Chroma).
• Strong knowledge of RAG architectures and prompt orchestration.
• Hands-on with LangChain/LangGraph for LLM workflows.
• Advanced Python (asyncio, type hints, Pydantic, SOLID).
• MLOps experience (MLflow, versioning, A/B testing); Langfuse is a plus.
• Experience in NLP and CV, including document understanding and OCR.
• Experience building feature pipelines and model serving.
• Familiarity with Hugging Face; LlamaIndex a plus.
• SQL database knowledge and SQL proficiency.

Responsibilities

• Build ML engineering platforms and components.
• Develop scalable backend systems, APIs, and microservices with FastAPI.
• Implement MLOps with KPI measurement, drift detection, and feedback loops.
• Deploy ML/Deep Learning models with focus on LLMs and GenAI.
• Integrate Azure OpenAI and other LLMs with retry logic and error handling.
• Stay updated on state-of-the-art LLMs, GenAI, and transformers.
• Scale algorithms for massive data under strict SLAs.
• Build and orchestrate model pipelines with feature engineering and inference.
• Write Python/SQL with OOP and asynchronous coding.
• Apply DI patterns and layered architecture (Service, Foundation, Orchestration, DAL).
• Create LLM observability (Langfuse) for prompts, tokens, costs, latency.
• Develop prompt management with versioning and fallbacks.
• Implement Celery/workflows for async processing.
• Design multi-tenant architectures with data isolation.
• Optimize LLM costs (caching, batching, token optimization).
• Integrate third-party APIs (document/OCR, cloud storage, ERP).
• Collaborate with client teams to gather technical requirements and deliverables.
• Write production-ready, testable code and perform reviews.

Skills

Python

7+ years

ML engineering

NLP

Computer vision

Problem solving

Team collaboration

Async programming

RAG architectures

LangChain/LangGraph

Education

Bachelor's or Master's in CS

Tools

FastAPI

SQLAlchemy

Pydantic

asyncio

LangChain

LangGraph

Hugging Face

Langfuse

Azure OpenAI

GPT-4

Weaviate/Pinecone/Chroma

SOLID principles

Job description

Intellectsoft seeks an experienced ML/backend engineer to build scalable ML platforms and backend systems in Spain. You will design and deploy APIs with FastAPI, implement MLOps for model KPI tracking, drift detection, and feedback loops, and orchestrate LLM workflows with LangChain.

You will integrate Azure OpenAI (GPT-4) and other providers, ensure async, DI patterns, and multi-tenant architectures while staying current on GenAI trends. Strong Python/CV/NLP background required.