Senior Applied AI Engineer

RaiseDesk Technologies Inc.; United States; Remote; USD 63,000 - 84,000; Full time

Benefits offered by this job

Fully remote (Canada)

Job summary

RaiseDesk Technologies Inc. is seeking an experienced production engineering professional to build data and applied AI systems for investor discovery.

The role focuses on shipping dependable features rather than research, with emphasis on pipelines, entity matching, and evaluation-driven improvements. The candidate will work on LLM-powered retrieval, ranking, drafting, classification, and summarization, ensuring low latency and cost efficiency while upholding safety guardrails.

Qualifications

• Five+ years of software or data engineering experience, including applied AI work.
• Demonstrated ability to design and implement data pipelines from ingestion to storage.

Responsibilities

• Create pipelines to ingest, clean, and organize third-party records at scale.
• Match entities across inconsistent sources while retaining data provenance.
• Build LLM-powered capabilities for retrieval, ranking, drafting, classification, and summarization.
• Own evaluation from test harness and metric design through to measuring the effect of changes.
• Manage latency, operating cost, safety guardrails, and fallback behaviour in model-backed features.
• Use AI coding agents in daily work and review and verify their output.
• Work independently and manage priorities and scope.

Skills

Python

SQL

PostgreSQL

MySQL

LLM applications

Evaluation frameworks

Data pipelines

AI coding agents

Independent work

Tools

PostgreSQL

MySQL

Job description

Build the data and applied AI systems behind investor discovery, including the pipelines that organize source records, the models and retrieval that rank results, and the evaluations that measure quality. This is a production engineering role focused on shipping dependable features rather than conducting research.

Responsibilities

• Create pipelines to ingest, clean, and organize third-party records at scale.
• Match entities across inconsistent sources while retaining data provenance.
• Build LLM-powered capabilities for retrieval, ranking, drafting, classification, and summarization.
• Own evaluation from test harness and metric design through to measuring the effect of changes.
• Manage latency, operating cost, safety guardrails, and fallback behaviour in model-backed features.
• Use AI coding agents in daily work and review and verify their output.

Requirements

• At least five years of software or data engineering experience, including recent applied AI work.
• Strong Python and SQL skills with relational databases such as PostgreSQL or MySQL.
• Production experience with LLM applications, including retrieval or RAG, prompt design, tool calling, and structured outputs.
• Experience owning evaluation frameworks and explaining how results show a system improved.
• Ability to build data pipelines from the ground up, covering schemas, ingestion, storage, and monitoring.
• Daily experience with AI coding agents and a disciplined approach to checking their output.
• Able to work independently and manage priorities and scope.

Benefits and work setup

The team is small and senior, and engineers are expected to make decisions, manage their own work, and surface problems early. The role is fully remote and must be performed from within Canada; applicants need legal authorization to work there.