Lead ML Engineer — Action Recognition for ATR

NestAI; Helsinki; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Occupational healthcare

Flex benefit

Lunch benefit

Regular team lunches and all-hands

Mac or PC choice

Holiday allowance

Phone benefit

Benefits expansion

Job summary

NestAI in Helsinki is building adaptive AI for defence, focusing on the ATR pipeline and action recognition from video streams. You’ll work on developing models that exploit temporal information from tracked objects and contribute to taxonomy building for different classes such as humans and vehicles.

As a senior/lead engineer, you will shape how action recognition fits into the detector, tracker, and classifier chain, design scalable solutions, and mentor junior colleagues on the team.

Qualifications

• Proven hands-on video analytics experience.
• Experience detecting and classifying actions from video streams (temporal/spatio-temporal).
• Track record of taking systems into production in an industry context.
• Ability to design and build a taxonomy of actions across object classes.
• Understanding of how action recognition fits into the ATR pipeline (detector, tracker, classifier).
• Nice to have experience with GStreamer, DeepStream or DLStreamer.

Responsibilities

• Develop action recognition models using temporal information from tracked objects.
• Build a taxonomy of actions for humans, vehicles, and other classes.
• Collaborate with detector and tracking teams to feed actions into NestAI’s ATR/S.A.L.U.T.E. pipeline.
• Mentor and guide junior team members.

Skills

Video analytics

Action recognition

Temporal modeling

Taxonomy design

Production deployment

3D vision

Team mentoring

Tools

GStreamer

DeepStream

DLStreamer

Job description

NestAI in Helsinki is building adaptive AI for defence, focusing on the ATR pipeline and action recognition from video streams. You’ll work on developing models that exploit temporal information from tracked objects and contribute to taxonomy building for different classes such as humans and vehicles.

As a senior/lead engineer, you will shape how action recognition fits into the detector, tracker, and classifier chain, design scalable solutions, and mentor junior colleagues on the team.