Senior Software Engineer - AI for Data Platforms (Hybrid)

Doist; New York (NY); Hybrid; USD 168,000 - 230,000; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Hybrid work model

Open-source involvement encouraged

Job summary

Astronomer empowers data teams to bring mission-critical software, analytics, and AI to life with Astro, the leading unified DataOps platform. We are building a global context layer for data and advancing search, code generation, and automated analysis using LLMs.

As a Software Engineer on this team, you will design and implement the foundation and applications around it, tackling hard challenges in data search, information retrieval, and AI-driven data products across organizations.

Qualifications

• Experience with large language models (LLMs) and data tooling.
• Familiarity with vector databases and embeddings for retrieval tasks.
• Proven ability to work across teams to ship data-driven features.
• Strong communication skills for both technical and non-technical audiences.

Responsibilities

• Design and build the context layer powering data modeling, semantic search, retrieval, and code generation.
• Experiment with LLMs and retrieval techniques to create developer tools that deliver insights.
• Turn research concepts into product features with R&D and product teams.
• Collaborate across the stack to release and scale AI-powered data products.

Skills

LLMs

Vector databases

Embeddings

Applied AI

Data engineering

Strong communication

Education

BS in CS or related field

Tools

Python

Apache Airflow

Job description

Astronomer empowers data teams to bring mission-critical software, analytics, and AI to life with Astro, the leading unified DataOps platform. We are building a global context layer for data and advancing search, code generation, and automated analysis using LLMs.

As a Software Engineer on this team, you will design and implement the foundation and applications around it, tackling hard challenges in data search, information retrieval, and AI-driven data products across organizations.