AI Engineer (Senior) – GenAI / Llms

Design and implement LLM-powered systems, including agents, retrieval-augmented generation (RAG) pipelines, and AI-driven workflows. Build and maintain backend APIs using Python and FastAPI, with robust integration of multiple LLM providers (e.g., OpenAI, AWS Bedrock, and others). Deploy, monitor, and operate AI services in cloud environments, ensuring reliability, performance, and observability in production. Collaborate closely with product managers, engineers, and stakeholders to translate business requirements into scalable AI solutions. Foster best practices in software engineering, security, and data governance within GenAI projects. Continuously evaluate emerging AI technologies and architectures to drive innovation and maintain a competitive edge. Participate in code reviews, testing, and documentation to uphold quality standards and maintainability.

Excellent English communication skills, both written and spoken. Strong soft skills including ownership, collaboration, and the ability to convey complex technical concepts clearly to cross-functional teams. A robust technical foundation in software engineering and AI, with demonstrated hands-on experience in deploying GenAI/LLM systems to production. Proficiency in Python and building REST APIs using FastAPI. Practical experience with LLMs/GenAI in production environments and integrating various LLM providers. Experience designing and implementing scalable cloud-based solutions on platforms such as AWS (or similar). Familiarity with containerization (Docker) and deployment orchestration (ECS, Kubernetes). Knowledge of LangChain or similar frameworks, LangGraph, RAG architectures, and experience with services like Amazon Bedrock, Textract, Pydantic AI, BAML. Prototyping tools such as Streamlit or Aestiva HTML/OS. Testing practices (pytest, Playwright) and monitoring/observability tools (CloudWatch, Prometheus, Grafana).

We provide the opportunity to participate in impactful and technically rigorous industrial data projects that drive innovation and professional growth. Our work environment emphasizes technical excellence, collaboration, and continuous innovation.

Niuro supports a 100% remote work model, allowing flexibility in work location globally. We invest in career development through ongoing training programs and leadership opportunities, ensuring continuous growth and success.

Upon successful completion of the initial contract, there is potential for long-term collaboration and stable, full-time employment, reflecting our long-term commitment to our team members.

Joining Niuro means becoming part of a global community dedicated to technological excellence and benefiting from a strong administrative support infrastructure that enables you to focus on impactful work without distraction.