AI Engineer

Sensor Tower; Lisboa; On-site; EUR 55,000 - 90,000; Full time

Job summary

Sensor Tower seeks an AI Engineer to build LLM-powered prototypes for gaming analytics. You will work on multimodal data such as screenshots and gameplay video, selecting appropriate models while balancing quality, speed, and cost.

Collaborate with data and software engineers to prototype, evaluate, and turn top ideas into live product features for our gaming analytics platform. Strong Python and TypeScript, with experience in LLM APIs and retrieval, are highly valued.

Qualifications

• Strong Python proficiency with ability to develop production-grade AI features.
• Experience with multimodal models: processing screenshots, images, or video.
• Hands-on experience building products on top of LLM APIs, not just chatbots.
• Understanding of RAG and vector search, and when to apply them.
• Ability to measure results and articulate performance.
• Ability to explain decisions clearly and work independently.
• Proficiency in interviewing in Russian and English.

Responsibilities

• Build AI prototypes for game analytics focusing on multimodal data (screenshots, images, video).
• Select and tune models (primarily Claude) balancing quality, speed, and cost.
• Collaborate with Data Engineers to build data pipelines for large game datasets.
• Measure quality and iteratively improve prototypes.
• Develop retrieval and multi-step pipelines.
• Translate top prototypes into real product features with engineers.

Skills

Python

TypeScript

Multimodal models

LLM APIs

RAG

Vector search

Independent work

English & Russian

Tools

FastAPI

LangGraph

OpenCV

PostgreSQL

S3

Kubernetes

React

Job description

Sensor Tower’s digital intelligence platform provides unparalleled insight into market trends, advertising, competitor’s strategies, and consumer/user audience across mobile, web, and gaming. Sensor Tower’s insights are trusted by more than 2,500 enterprises worldwide across tech, retail/commerce, entertainment/media, gaming, consumer packaged goods and finance.

Our mobile gaming portfolio includes AppMagic and Playliner, which help game developers and publishers understand the mobile games market and how top games run their LiveOps.

We’re looking for an AI Engineer to build LLM-powered prototypes for our gaming analytics products

What You’ll Do

• Build AI prototypes for game analytics, with a focus on multimodal data: screenshots, images and gameplay video. For example, recognizing LiveOps events from in-game screenshots or extracting what changed in a game update.
• Choose and use the right models for each task (mainly Claude), balancing quality, speed and cost.
• Build data pipelines with our Data Engineer to run models on large volumes of game data.
• Measure quality so we know what works and what doesn’t.
• Build retrieval and multi-step pipelines.
• Turn the best prototypes into real product features together with our engineers.

Our tech stack

Python, FastAPI, LangGraph, OpenCV, PostgreSQL, S3, Kubernetes, TypeScript, React

What We’re Looking For

• Strong Python (TypeScript is a plus).
• Experience with multimodal models: screenshots, images or video.
• Hands‑on experience building products on top of LLM APIs, not just chatbots.
• Understanding of RAG and vector search, and when they’re not needed.
• You measure results and can show how well your solution works.
• You can work independently and explain your decisions clearly.
• Ability to pass technical interview both in Russian & English.

What We’d Be Particularly Excited About

• Interest in or experience with mobile games, LiveOps or market analytics.
• Hands on experience in building AI projects
• Experience with LangGraph, LlamaIndex or similar frameworks, and an opinion on when they’re worth using.

We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.