Nir Herscovici

Part 1 · Leadership

Leadership

Herscovici ran manufacturing technology for melting, forging and inspection across the company's titanium plants: a 22-person R&D organization, a seven-figure budget, the company's de facto head of machine learning, and the technology standard that every site builds to. He presented roadmaps directly to the COO, won CEO approval to expand the organization, and was the company's technical face to nine jet-engine OEMs through a material-defect investigation.

Results

• Cut scrap and defects 30%+, raised uptime and throughput 10%+ and cut recordable incidents 25%+ across the plants running these systems, by taking 15+ perception and control systems into 24/7 production on one standard platform.
• Delivered the technology package of a $500M greenfield titanium plant, measured by seven process units instrumented from site inception and milestones met, by serving as de facto chief engineer for all site technology and owning the $5M+ package, the contractors, the equipment OEM and the schedule.
• Resolved a first-of-its-kind material-defect investigation for nine jet-engine OEMs, measured by 1,132 production runs reviewed and the defect resolved, by directing 50+ people across sites as customer-facing technical lead and cutting the projected review cost about 80%.
• Set the company's standard for future sites, measured by adoption of the reference architecture, hardware and vendor standards, rollout playbook and maintenance procedures, by proving the platform at existing plants and writing it into the framework.
• Built the organization that maintains all of it, measured by promotions for every engineer and an internship structure adopted company-wide, by hiring, recruiting and advising directly for six years.
• Turned the function's work into protected IP, measured by four patent filings (US 12,332,611 B2 granted; US 2025/0119992 A1 and US 2025/0277286 A1 published; one application and one provisional pending) and two conference awards, by taking each system from R&D prototype to production before filing.

Business impact

Operating model

• A business case before capital. ROI, trade studies and a payback target for every project; stage-gate validation from the pilot line to production.
• An assurance case before fielding. FMEA and hazard analysis with documented safety cases, model acceptance criteria, calibrated thresholds and runtime monitors; a formal on-call and incident-response process for systems in service.
• Build for the plant. Standard hardware, in-house code and written maintenance procedures, so plant engineers own what R&D delivers.
• Grow the team from the inside. Interns to engineers, graduate researchers advised personally, promotions argued for every engineer.
• A visible cadence. Weekly schedules against plan, weekly customer calls during the investigation, roadmaps and Gantt schedules to executives; lightweight agile practice inside the team.

Title note: PCC has no chief-engineer title. "De facto chief engineer" describes the role he held at the greenfield plant, not a title.

Part 2 · The corporate technology roadmap

Build once, then scale across plants and repurpose across processes

Herscovici set the multi-year technology direction for machine learning, vision, sensing, inspection and automation across the company's plants and processes. The roadmap matured from isolated AI projects into a manufacturing-systems platform, and from one plant's tools into a catalog of capabilities: each one built and hardened on one process, then copied to other plants and repurposed for other processes and divisions. The model is a standard core with a local last mile: the hardware, software and data architecture are shared; mounting, thresholds, operator displays and process logic are site-specific.

The same failure modes repeated across facilities: manual supervision, fragile data integration, underestimated hardware complexity, fragmented ownership and reinvention. Each became a standardization priority: preferred hardware stacks, reusable software modules, a signal and storage architecture, documentation and acceptance-test packages, IT and security templates, and named ownership for updates and retraining, so no deployment is engineered from scratch.

Part 3 · The portfolio

Six of the 15+ production systems

Herscovici wrote production code for every one of these and led the organization that maintains them. The full engineering record, with decisions, sketches, mathematics and limits, is in the chief-engineer edition.

• Machine perception and rare-event detection

• 01 Rare-event detection and tracking in production video (image-suitability method: U.S. application pending)Resolved a first-of-its-kind jet-engine material defect for nine OEMs, measured by 95% fewer false positives at 95%+ recall, 100× less manual review and an ~80% lower projected review cost, by designing a three-stage detector with multi-target tracking and a domain-shift monitor, and running the review on a weekly schedule as customer-facing technical lead.

• Vision systems for dimensional metrology and inspection

• 02 A measurement that gates a process step: weld rating (provisional patent filed)Replaced a visual weld judgment with a reproducible gate on the run, measured by a 1-to-5 rating in 5–10 seconds, ~85% agreement with an engineer mid-development and a PLC interlock on every failed weld, by building two segmentation networks, a radial-coverage geometry and a fail-closed PLC and MES integration.
• 03 Multi-sensor fusion on one record: straightness, hot and coldMeasured bar straightness at the forge press in real time, measured by 4K video collected 24/7, hot results benchmarked against the cold laser scanner on the same forged bars and results on the operator's display at the press, by combining semantic segmentation with least-squares edge slopes and fusing both instruments on one MES record.
• 04 Laser metrology and in-process control (US 2025/0277286 A1)Put inspection on a measured footing, measured by about 80% of final-stage molds at one plant scanned, an LMPC 2024 Most Innovative Work Award and a pending patent on shelf detection, by building a laser-and-camera mold scanner and the in-process measurements that feed arc control.

• Controls, mechanical design and automation

• 05 Closed-loop process control from vision (US 12,332,611 B2)Automated end-of-run power cutback in production for 3+ years, measured by 85%+ lower prediction error within four months and U.S. Patent 12,332,611, by replacing a licensed, hard-wired first-generation system with an in-house CNN-plus-regression trigger connected to the process unit at two interface points.
• 06 Electromagnetic actuation and control (US 2025/0119992 A1)Closed a ~2% product-yield gap between two plants, measured by 19+ cast products at the top surface rating, by designing a twin-coil arc-steering retrofit with three-phase PWM drives, PLC control and camera-based verification of arc rotation.