Senior Action-Recognition ML Engineer – Edge AI

NestAI; Tampere; On-site; EUR 90,000 - 150,000; Full time

Benefits offered by this job

Occupational healthcare

Epassi Flex benefit

Lunch benefit

Regular team lunches and all-hands

Mac or PC choice

Holiday allowance

Phone benefit

Benefits expansion as we grow

Job summary

NestAI seeks a senior/lead engineer to shape action recognition within its ATR pipeline for unmanned and command systems. You will influence how actions are modeled and integrated, and you’ll guide junior engineers on the team.

You will develop temporal action recognition approaches, build an action taxonomy across objects, and collaborate with detector/tracker teams to feed classifications into NestAI's reporting pipeline.

Qualifications

• Previous industry experience with production-ready systems.
• Hands-on video analytics experience.
• Proven experience detecting and classifying actions from video streams (temporal/spatio-temporal).
• Ability to design and build a taxonomy of actions across objects.
• Understanding of how action recognition fits into the ATR pipeline (detector, tracker, classifier).
• Experience with GStreamer, DeepStream (NVIDIA) or DLStreamer (Intel) is a plus.
• Background in 3D vision is a plus.
• Experience with temporal/sequence modeling architectures for video (3D CNNs, video transformers) is a plus.
• Background in building action taxonomies or ontologies for computer vision systems is a plus.

Responsibilities

• Develop action recognition models that leverage temporal information from tracked objects.
• Build and maintain a taxonomy of actions tailored to different object classes.
• Collaborate with detector and tracking teams to feed classified actions into the ATR/SALUTE reporting pipeline.
• Mentor and guide junior team members.

Job description

NestAI seeks a senior/lead engineer to shape action recognition within its ATR pipeline for unmanned and command systems. You will influence how actions are modeled and integrated, and you’ll guide junior engineers on the team.

You will develop temporal action recognition approaches, build an action taxonomy across objects, and collaborate with detector/tracker teams to feed classifications into NestAI's reporting pipeline.