Applied physicist and engineer, 15+ years. Put me on a messy, physical, high-consequence problem that crosses disciplines and has to ship — not demo.
Recent: 6 years at Agilent building production ML over instrument telemetry: fleet-wide failure prediction, and a RAG/LLM system for 300+ field engineers taken from prototype to production (including the confidence logic for when it answers vs. hands off to a human). Cut data-prep time 8x.
Before that I built scientific instruments from scratch (a fiber-based STED nanoscope and an OCT microscope) so I know data from the sensor up, not just after it lands in a warehouse. Earlier: DoD hardware reliability (former TS/SCI), precision timing, published detector-physics work.
Strongest where software meets the physical world: instrumentation, sensor data, ML that has to be right because being wrong has consequences. I own problems end to end, and I'll tell you when the result isn't trustworthy yet.
Open to full-time or contract. Health/medical-device mission a strong plus.
Applied physicist and engineer, 15+ years. Put me on a messy, physical, high-consequence problem that crosses disciplines and has to ship — not demo.
Recent: 6 years at Agilent building production ML over instrument telemetry: fleet-wide failure prediction, and a RAG/LLM system for 300+ field engineers taken from prototype to production (including the confidence logic for when it answers vs. hands off to a human). Cut data-prep time 8x.
Before that I built scientific instruments from scratch (a fiber-based STED nanoscope and an OCT microscope) so I know data from the sensor up, not just after it lands in a warehouse. Earlier: DoD hardware reliability (former TS/SCI), precision timing, published detector-physics work.
Strongest where software meets the physical world: instrumentation, sensor data, ML that has to be right because being wrong has consequences. I own problems end to end, and I'll tell you when the result isn't trustworthy yet.
Open to full-time or contract. Health/medical-device mission a strong plus.
Remote: Yes (also open to onsite in Boulder County)
Willing to relocate: No
Technologies: Python, SQL, applied ML, RAG/LLM systems, embeddings, signal processing, data pipelines, instrumentation, optics/photonics, C++, MATLAB, AWS
Résumé/CV: heffern.net/rob
Email: Robert.Heffern@gmail.com
Applied physicist and engineer, 15+ years. Put me on a messy, physical,
high-consequence problem that crosses disciplines and has to ship — not demo.
Recent: 6 years at Agilent building production ML over instrument telemetry —
fleet-wide failure prediction, and a RAG/LLM system for 300+ field engineers taken
from prototype to production (including the confidence logic for when it answers vs.
hands off to a human). Cut data-prep time 8x.
Before that I built scientific instruments from scratch — a fiber-based STED
nanoscope and an OCT microscope — so I know data from the sensor up, not just after
it lands in a warehouse. Earlier: DoD hardware reliability (former TS/SCI), precision
timing, published detector-physics work.
Strongest where software meets the physical world: instrumentation, sensor data, ML
that has to be right because being wrong has consequences. I own problems end to end,
and I'll tell you when the result isn't trustworthy yet.
Open to full-time or contract. Health/medical-device mission a strong plus.
Remote: Yes (also open to onsite in Boulder County, CO)
Willing to relocate: No
Technologies: Python, SQL, applied ML, RAG/LLM systems, embeddings, signal processing, data pipelines, instrumentation, optics/photonics, C++, MATLAB, AWS
Résumé/CV: https://robheffern.palaich.net/cv/
Email: Robert.Heffern@gmail.com
Applied physicist and engineer, 15+ years. Put me on a messy, physical, high-consequence problem that crosses disciplines and has to ship — not demo.
Recent: 6 years at Agilent building production ML over instrument telemetry: fleet-wide failure prediction, and a RAG/LLM system for 300+ field engineers taken from prototype to production (including the confidence logic for when it answers vs. hands off to a human). Cut data-prep time 8x.
Before that I built scientific instruments from scratch (a fiber-based STED nanoscope and an OCT microscope) so I know data from the sensor up, not just after it lands in a warehouse. Earlier: DoD hardware reliability (former TS/SCI), precision timing, published detector-physics work.
Strongest where software meets the physical world: instrumentation, sensor data, ML that has to be right because being wrong has consequences. I own problems end to end, and I'll tell you when the result isn't trustworthy yet.
Open to full-time or contract. Health/medical-device mission a strong plus.