onsite
Founding AI Engineer - Advatix
AI Engineer
Lead the design and deployment of AI and backend systems for a digital public‑safety analyst, building scalable RAG pipelines on AWS and integrating NLP models to transform unstructured evidence into searchable insights.
About the role
Key Responsibilities
- Architect and ship end‑to‑end machine learning pipelines that ingest, process, and retrieve information from large volumes of unstructured data such as calls, reports, and transcripts.
- Design and maintain a robust backend on AWS, ensuring high availability, scalability, and security for the digital analyst platform.
- Implement Retrieval Augmented Generation (RAG) workflows, integrating state‑of‑the‑art NLP models to provide context‑aware answers to investigators.
- Collaborate closely with founders, product, and investigative teams to translate domain requirements into technical solutions.
- Continuously evaluate and adopt new AI technologies, frameworks, and best practices to keep the platform at the cutting edge.
Requirements
- Strong proficiency in Python and experience building production‑grade ML systems.
- Hands‑on expertise with NLP, RAG, and retrieval‑based architectures.
- Deep knowledge of AWS services (S3, Lambda, SageMaker, DynamoDB, etc.) and experience deploying scalable solutions.
- Solid background in data engineering, including data ingestion, transformation, and storage.
- Excellent problem‑solving skills and a collaborative mindset in a fast‑moving startup environment.
Skills
pythonmachine learningawsnlp