Senior Python Backend Engineer - AI/LLM Platform (Remote)

Intellectsoft; Argentina; Remote; ARS 2,000,000 - 4,000,000; Full time

Benefits offered by this job

Udemy courses of your choice

Team-building events

Flexible hours & work setup - remote

Job summary

Intellectsoft is seeking an experienced ML Engineer to design and deploy scalable backend systems and ML workflows for AI-powered platforms. You will integrate LLMs (GPT-4/vision) and vector databases, build robust MLOps, and ensure production-grade reliability in a fast-paced, collaborative environment.

Key focus areas include model pipelines, observability, prompt management, and cost optimization for large-scale AI deployments across healthcare and other domains.

Qualifications

• Bachelor’s or Master’s in CS or related field.
• 7+ years Python coding with ML focus.
• 2+ years hands-on ML and production LLM systems.
• 3+ years APIs with FastAPI, async patterns, rate limiting, SQLAlchemy.
• Design maintainable systems via DI, interfaces, AB classes.
• Experience with vector DBs (Pinecone, Weaviate, Chroma) and hybrid search.
• Strong RAG knowledge: retrieval, reranking, context assembly, generation.
• LangChain/LangGraph for LLM workflows.
• Advanced Python: async/await, type hints, Pydantic, SOLID.
• MLOps with MLflow, model versioning, A/B testing; Langfuse a plus.
• Experience NLP/vision incl. document understanding, OCR, GPT-4 Vision.
• Feature pipelines, real-time/batch inference, model serving.
• Hugging Face experience required; LlamaIndex a plus.
• SQL and database familiarity.
• Strong problem solving in fast-paced, team environment.

Responsibilities

• Build and refine ML engineering platforms and scalable backend systems with FastAPI.
• Implement MLOps: KPI measurement, drift detection, feedback loops.
• Deploy and operationalize ML/Deep Learning models with focus on LLMs/GenAI.
• Integrate Azure OpenAI and other LLMs with retry logic and error handling.
• Maintain up-to-date knowledge of LLMs, GenAI, transformer architectures.
• Scale ML algorithms for large data under strict SLAs.
• Create model pipelines: feature engineering, inference, training loops.
• Write Python/SQL with OO design and async programming.
• Apply DI patterns and layered architecture (Service, Foundation, Orchestration, DAL).
• Build LLM observability (Langfuse) to track prompts, tokens, costs, latency.
• Develop prompt management with versioning and fallbacks.
• Set up Celery-like workflows for async tasks and pipelines.
• Design multi-tenant data isolation architectures.
• Optimize LLM costs: caching, batching, token optimization.
• Integrate third-party APIs and cloud storage / enterprise systems.
• Collaborate with client teams to gather requirements and provide technical input.
• Deliver production-ready, testable, maintainable code; handle edge cases.
• Ensure quality via design/code reviews and OpenAPI/Swagger docs.

Skills

Python

ML engineering

LLMs

FastAPI

Async patterns

SQLAlchemy

Pinecone

Weaviate

Chroma

LangChain

LangGraph

MLOps

Langfuse

Hugging Face

OCR

GPT-4 Vision

SQL

Education

Bachelor’s or Master’s in Computer Science

Tools

FastAPI

LangChain

LangGraph

Azure OpenAI

Azure OpenAI GPT-4

Pinecone

Weaviate

Chroma

SQLAlchemy

MLflow

Langfuse

Hugging Face

OCR tooling

Job description

Intellectsoft is seeking an experienced ML Engineer to design and deploy scalable backend systems and ML workflows for AI-powered platforms. You will integrate LLMs (GPT-4/vision) and vector databases, build robust MLOps, and ensure production-grade reliability in a fast-paced, collaborative environment.

Key focus areas include model pipelines, observability, prompt management, and cost optimization for large-scale AI deployments across healthcare and other domains.