Algorithms Team Lead

Description:

Exodigo is the leading underground mapping solution for non-intrusive discovery. Our platforms combine multi-sensor fusion, 3D imaging, and AI technologies to create complete, accurate underground maps that enable confident decision-making for customers across the built world. We transform the project lifecycle for our customers, who include key community stakeholders in the utilities, transportation and government sectors.

Our customers are the utilities, transportation agencies, and government bodies that build the world's infrastructure — LA Metro, Caltrans, National Grid, Israel Railways, and 100+ teams worldwide. To date we've de-risked $75B in infrastructure investment and mapped 86.1M square feet of ground.

We are experiencing sky-rocketing growth and closed a historically large $96M Series B round in July of 2025.

Lead the algorithms team within the Geotech group. The team owns the full processing chain, from the raw signal acquired in the field to the output the customer sees: denoising, reconstruction, inversion, detection and characterization of subsurface targets, and quantification of confidence. The data is real field data: noisy, non-ideal, and collected across a diverse sensor suite (GPR, ERT, seismic, EM, magnetometry).

This role combines team leadership with hands-on algorithm development, with a strong focus on setting priorities, deciding which directions to pursue or stop, and staying deeply involved in the technical work. This is not management from a distance.

Management responsibilities

• Translate business needs, customer requirements, and field constraints into a clear algorithmic roadmap with measurable goals and timelines
• Set priorities across parallel workstreams, including closing down directions that aren't maturing and freeing the resources tied to them
• Protect the team's focus. Shield team members from interruptions and ad-hoc requests that don't serve the roadmap, and manage expectations with the people making those requests
• Direct people management: individual goals, ongoing feedback, professional development, hiring and onboarding
• Build a measurement culture: define validation methodology, performance metrics, dataset and ground-truth management. Prevent "it looks good" from replacing quantitative proof
• Own output quality: code review, engineering standards, reproducibility of results, and documentation good enough to hand work between people
• Report status, risks, and decision points to management on an ongoing basis

Hands-on engineering

• Independently develop and prototype algorithms on the team's hardest problems
• Get into the data: analyze failure cases, investigate anomalies, understand what is actually happening in the signal
• Work closely with field teams, including going out to the field as needed, to understand noise sources and physical limitations firsthand
• Review the team's work at a deep technical level rather than signing off on results

• Proven experience developing algorithms in signal processing, on real physical data (not simulation only)
• Strong DSP fundamentals: time- and frequency-domain analysis, filtering, deconvolution, SNR, sampling
• Experience with inverse problems and/or reconstruction and imaging (tomography, migration), including handling ill-posed problems and regularization
• Full command of Python and the scientific stack (NumPy/SciPy and related), with the ability to write clean, maintainable code rather than one-off scripts
• Prior management experience, or at minimum proven technical leadership of several developers and an end-to-end project
• Demonstrated ability to make decisions under uncertainty and prioritize between competing directions
• Professional-level Hebrew and English

Nice to Have

• Background in geophysics, or in any field that measures a physical phenomenon through a complex medium (medical imaging, sonar, radar, NDT, seismology, acoustics)
• Experience with ML/DL applied to signals and imaging, and the judgment to know when a classical approach is better
• Experience taking an algorithm from R&D into production
• Familiarity with physical models and forward modeling