Machine Learning Engineer – NLP, LLMs, Python

Job not on LinkedIn

13 hours ago

Apply Now

Receive Emails with Similar Jobs

Leega

WebsiteLinkedInAll Job Openings

API • Artificial Intelligence • Cloud Solutions

Leega is a leading technology solutions provider in Latin America, specializing in data analytics and cloud solutions. As the first company in the region certified by Google Cloud for Data Analytics, Leega offers a range of services including application development, machine learning, and risk management analytics. The firm partners with major cloud services such as AWS and Microsoft Azure to help businesses enhance their data management and transition effectively to the cloud, ultimately driving digital transformation and innovation.

201 - 500 employees

Founded 2010

🔌 API

🤖 Artificial Intelligence

📋 Description

• Develop accelerated text extraction and enrichment pipelines. • Implement hybrid information extraction solutions (rule-based + statistical models + LLMs). • Build robust model inference APIs using FastAPI and Pydantic. • Create and maintain model observability and performance dashboards (e.g., Grafana with custom metrics). • Contribute to knowledge transfer to enable the client's future autonomy. • Work within Agile methodologies, including two-week sprints, frequent demos, and retrospectives. • Work model: Remote.

🎯 Requirements

• Programming language: Advanced proficiency in Python 3.11+. • Core NLP and deterministic extraction: Strong expertise with spaCy 3.7+, including use of PhraseMatcher, DependencyMatcher, and rule-based matching (EntityRuler). • LLMs and frameworks: Experience with Transformers 4.40+ (Hugging Face). • RAG (Retrieval-Augmented Generation): Practical experience implementing RAG using vector stores (e.g., Qdrant, Pinecone, or Chroma). • Prompting and orchestration: Experience with frameworks such as LangChain, LlamaIndex, or DSPy for few-shot/zero-shot prompting techniques. • APIs and services: Experience developing REST/gRPC APIs (using FastAPI + Pydantic). • MLOps and experimentation: Familiarity with experimentation tools such as MLflow, Weights & Biases, or Comet ML. • Nice-to-haves (not required): Experience fine-tuning and instruction-tuning open-source LLMs in Brazilian Portuguese (e.g., Llama-3.1, Mistral, Mixtral, Gemma-2).

🏖️ Benefits

• Leega is inclusive — we’d be very happy to have you on our team. Join us in building our story and shaping our future. • Continuous training and development.