Senior Backend & AI Engineer - Secure Systems & LLMs

Alldus; New York (NY); On-site; USD 135,000 - 215,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

Alldus is hiring a Member of Technical Staff - Backend & AI in New York to build secure, reliable backend services and to integrate AI capabilities that help law professionals search and interpret complex evidence.

The role entails deploying LLMs and VLMs, developing RAG pipelines, and creating agentic workflows across multiple data sources, with ownership from investigation to deployment in a fast-paced startup environment.

Qualifications

• Extensive backend experience with secure, distributed systems.
• Proficient in Python; comfortable with multiple languages and infra.
• Hands-on deployment of LLMs/VLMs in production.
• Experience building RAG pipelines for unstructured data.
• Skilled in semantic modelling and data reasoning.
• Able to own projects in a fast-paced startup.
• Strong troubleshooting of production systems.

Responsibilities

• Build and maintain secure, reliable backend services and distributed systems.
• Integrate and deploy large language models, vision-language models and other machine learning technologies into production.
• Develop RAG pipelines to process, retrieve and search unstructured evidence.
• Build tools for querying, modelling and reasoning across structured data.
• Create agentic workflows that reason, plan and act across multiple data sources.
• Assess emerging AI models, infrastructure and engineering methods to improve platform capabilities.
• Take ownership of technical projects from initial investigation through development, deployment and ongoing support.
• Resolve production issues and respond to urgent technical and operational requirements.

Skills

Backend systems

Python

LLMs deployment

RAG pipelines

Structured data

Agentic AI

Ownership mindset

Troubleshooting

Job description

Alldus is hiring a Member of Technical Staff - Backend & AI in New York to build secure, reliable backend services and to integrate AI capabilities that help law professionals search and interpret complex evidence.

The role entails deploying LLMs and VLMs, developing RAG pipelines, and creating agentic workflows across multiple data sources, with ownership from investigation to deployment in a fast-paced startup environment.