Senior Perception Engineer

Teleo, a Havoc company, is a robotics company that transforms construction heavy equipment, including loaders, dozers, excavators, and trucks, into autonomous robots for commercial and defense applications. Our technology enables a single operator to supervise and control multiple machines simultaneously, delivering significant productivity gains while improving operator safety and comfort.

Teleo was founded by a team of experienced technology leaders who previously led the development of Lyft's Self-Driving Car program and Google Street View. Teleo recently announced its merger with Havoc AI, a fast-growing defense technology company developing coordinated fleets of autonomous maritime vessels.

This is a unique opportunity to join a team building technology with real-world impact. You will work on cutting-edge 100,000-pound autonomous robots and engineer complex systems at the intersection of hardware, software, robotics, and AI.

Build perception algorithms and architecture, fusing multiple sensor modalities and supporting an evolving set of novel object classes, in order to provide safe operations for heavy machinery working on constructions and mining sites.

Re-use, adapt and extend existing perception algorithms (such as those commonly used in AV applications) to be applied to Teleo's operational domain and develop novel multi-modal perception algorithms

(Re-)Train models as Teleo's operational domain evolves

Develop auto-annotation and auto-labeling tools using SoTA methods, such as VLMs

Define evaluation protocols that correlate with on-ground performance

Drive active learning: select the right data

Integrate tightly with MLOps for continuous deployment

M.S. or higher in Computer Science, Computer Engineering, Robotics, Electrical Engineering, or a related technical field.

3+ years in applied ML with large-scale datasets

Strong Python + PyTorch

Experience shipping perception or ML systems into production

Systems thinker: understands data, models, infra as one system

Auto-annotation techniques like VLM-based labeling

Model evaluation beyond single metrics (failure modes, edge cases)

Perception tasks: detection, segmentation, depth, tracking

Multi-modal data (camera, LiDAR, radar)

Dataset management & slicing

Experience with synthetic data or simulation

Large-scale data pipelines (Parquet, Arrow, object storage)