When the Wall Street Journal, Bloomberg, or the New York Times reports on the streaming wars, the numbers often come from Antenna. Our data and models are the market standard for the Subscription Economy, trusted by the most recognized brands in media and entertainment to decide what to make, what to charge, and how to grow. The models you build here get cited, and they shape decisions at the highest levels of the industry.

We are also AI-first in practice. Every team member works with frontier AI tooling (Claude, Gemini, OpenAI) as a daily driver, and our AI Council pushes everyone to be an AI driver, not a passenger. If you want a team where agentic coding, LLM pipelines, and rigorous evals are the everyday norm you will fit right in.

We're looking for a talented Data Scientist with expert Python skills and a passion for inventing new data products. You'll design, prototype, and ship the models behind our newest offerings: generative models on mixed data sources, predictions of subscriber behavior, and LLM-powered pipelines with the evals to prove they work. You'll work closely with data scientists and engineers to take ideas from first experiment to production at market scale. If you love turning ambitious modeling ideas into shipped products in a data-driven company, this job is for you!

Antenna is a remote-first company, and we are looking for candidates who can work during US business hours. Preferably, you should be based in a US time zone (Eastern, Central, Mountain, or Pacific). You will report to the Director, Data Science.

What You’ll Do

• Build models and data products that make it all the way to production for our two flagship products: Subscriber Views, which connects what people watch to why they subscribe, and Subscriber Metrics, the market standard for sign-ups, churn, and retention
• Solve the modeling problems that unlock new product capabilities - from viewership attribution and sports data to generative models on mixed data sources and new models for TV providers (MVPDs)
• Dig into large, messy datasets to find the trends and patterns that turn into shipped features, add the functions, classes, and tools to our core Python data science library that the rest of the team builds on, and make existing code faster and able to handle more data
• Take on Antenna R&D work: explore new datasets and methods to answer real business questions and present what you find to senior stakeholders
• Build LLM-powered pipelines and agents, and treat evals as a core deliverable: validated outputs, eval sets with clear pass/fail checks, and evidence they catch problems human review misses
• Use agentic coding tools as part of your daily workflow - plan first, write tests and instructions up front, review every change - while still designing, debugging, and defending clear, well-documented, testable code of your own
• Collaborate with cross-functional stakeholders, including our co-founders, and clearly explain complex technical and system design decisions

Who You Are

• You have 2+ years of experience building machine learning models and data products in Python, with the engineering skills to take them from prototype to production
• Expert in Python with strong object-oriented design, software system design, and experience building high-quality, testable, production-grade code
• Solid grasp of machine learning concepts and how models are built, used, and evaluated
• Strong SQL skills working with large, complex datasets
• Experience using Git, and comfortable working in cloud environments (GCP preferred) to pull and process data (e.g., BigQuery) and run your analytical work.
• Excellent problem-solver, skilled at debugging complex distributed systems and optimizing them for performance and scale
• Advanced English proficiency (B2-C1) with strong communication, teamwork, and consulting skills; able to clearly explain complex technical and system design decisions
• You use agentic coding tools (Claude Code, Cursor, or Codex CLI) as part of your daily workflow: plan first, write tests and instructions up front, and review every change before accepting it. You can still design, debug, and defend your own work without AI assistance, and our interview process tests this directly
• You measure whether an LLM is actually right: you verify model outputs against ground truth by default, build simple eval sets or labeled samples to compare approaches, and can give a concrete example of a hallucination or silent error you caught.

Bonus

• Experience in or passion for the Subscription Economy, especially media and entertainment; experience working with media data or data clean rooms
• Hands-on experience with deep learning frameworks (PyTorch or TensorFlow), MLOps practices (like model monitoring), or synthetic data and generative models (e.g., GANs, VAEs, CTGAN)
• Experience with large-scale data processing tools (e.g., Apache Spark/PySpark, Dask)
• Experience deploying and scaling services in the cloud (Docker, Cloud Run, GKE, Dataproc)
• Experience building and shipping LLM-powered agents or pipelines with an orchestration framework (LangGraph, Pydantic AI, or OpenAI Agents SDK), including custom tool definitions, agent state and memory, and human review steps
• Advanced evaluation and observability practices: LLM-as-a-judge calibration, automated regression suites, and tracing tools (Langfuse, LangSmith, or Braintrust)
• Familiarity with RAG and context engineering for grounding model responses in proprietary data, or experience using LLMs for testing pipelines and QA workflows
• Experience with BI tools (Looker, Tableau), building Python libraries that others use, or open-source contributions

Antenna's Tech Stack (Required proficiency listed if applicable)

• Languages: Python (expert), SQL (strong)
• Large-Scale Data Processing: Apache Spark/PySpark (or similar like Dask)
• Cloud Platform: Google Cloud (Dataproc, BigQuery, Cloud Storage, Cloud Run, Cloud Build, GKE strong experience expected)
• Version Control: Git (expert)
• MLOps & Orchestration: Familiar with tools like Airflow, Kubeflow, Vertex AI Pipelines
• Containerization: Docker, Kubernetes
• Data Analysis Libraries: Pandas, NumPy (very good with these)
• Machine Learning: scikit-learn, TensorFlow/PyTorch (understand how to get them to production)
• AI Tools: Claude, Gemini, OpenAI offerings

Antenna Benefits

• Work from anywhere, during US business hours
• Competitive compensation, including participation in Antenna equity program
• Mentorship from experienced executives
• Opportunity to grow and impact a rapidly growing start up 
• Travel to In-person team off-sites (visa-permitting)
• And more!