The San Francisco Office of the Chief Medical Examiner (SFOCME) moved to a $65M state-of-the-art facility in 2018. The 52,000 sq. ft. facility includes a fully accredited laboratory with approximately $5M invested in new technologies including a Sciex QT0F X500R and 6500+ QTrap with accompanying Ultra High Performance Liquid Chromatography for high throughput analysis. In-house histology services are with TissueTek automatic tissue processor, stainer and cover-slipper configured to ensure optimal output. The facility was designed to specifically enhance the communication between the different divisions and most importantly enhance the work experience of staff. A private second story office overlooking the San Francisco Bay and marsh lands, with secure parking on-site and conference suites outfitted with video teleconferencing capabilities.

To meet an OCME mission in informing public health initiatives, the OCME produces several key reports on accidental overdoses, and DUID, DFSA, and other human performance casework.

Following the implementation of a new in-house built SQL and python-based laboratory information management system (LIMS), and a comprehensive validated QTOF forensic toxicology testing method, the SFOCME has the opportunity to interrogate such systems to identify the following:

• Enhanced Efficiency and Throughput: Faster data analysis and case turnaround times enable the lab to handle higher case volumes effectively.
• Improved Sensitivity and Specificity: ML algorithms provide better accuracy in detecting compounds, lowering false positives and false negatives, and increasing data reliability.
• Real-Time Data Insights: Immediate detection of emerging drug trends and flagging of data anomalies help the lab stay ahead of potential risks.
• Automated Quality Control and Error Reduction: AI-enhanced error detection and quality control ensure robust, high-quality data management.
• Predictive Case Management and Resource Allocation: Case outcome predictions and optimized resource use improve efficiency and case prioritization.
• Cost Savings and Resource Optimization: Automation of repetitive tasks reduces costs and lets staff focus on high-value tasks.
• Scalability and Adaptability to New Substances: AI infrastructure enables easy updates as new drugs emerge, ensuring the lab’s relevance and adaptability.
• Enhanced Reporting and Transparency: More detailed and transparent reports improve court case support and forensic analysis explanations.
• Cross-Disciplinary Collaboration: AI-enabled data sharing fosters joint research and benchmarks across forensic labs.
• Professional Development and Skill Building: AI integration encourages staff learning, expanding lab expertise and innovation potential.

Appointment Type: Temporary Exempt (TEX), this position is excluded by the Charter from the competitive Civil Service examination process and shall serve at the discretion of the Appointing Officer.

The employee can consider the opportunity to undertake a PhD simultaneously, which can be discussed with the appointing officer. 

Compensation:  $45.8750 hourly

Application Opening: November 1, 2024
Application Deadline: Applicants are encouraged to apply immediately as this recruitment may close at any time, but not before November 15, 2024.

Late or incomplete submissions will not be considered. Mailed, hand delivered or faxed documents/applications will not be accepted.

Under the guidance of the Chief Forensic Toxicologist and Director of the Forensic Laboratory Division, the forensic laboratory seeks a highly motivated candidate to investigate, design, and help implement AI and machine learning (AI/ML) models that enhance laboratory workflows and improve case processing. This role will focus on integrating AI and ML into key lab processes to improve drug identification in untargeted suspect screening of Quadrupole Time-of-Flight Mass Spectrometry (QTOF) data, as well as developing predictive models to assist in case conclusions. By contributing to the development of an SQL- and Python-based Laboratory Information Management System (LIMS), the student will be instrumental in creating infrastructure that enhances efficiency, accuracy, and scalability in forensic science.

This role offers an opportunity to help transform forensic laboratory practices by implementing AI-driven infrastructure that enables faster case processing, more accurate drug detection, real-time data insights, and automated quality control. The candidate’s contributions will enhance lab adaptability, reduce human error, optimize resources, and improve forensic reporting—creating a future-ready, data-driven laboratory environment.

Education:  Possession of a Bachelor's degree from an accredited college or university in a life science or physical science with 16 semester hours in general and organic chemistry courses, a statistics course, and two (2) analytical and/or interpretive courses in forensic toxicology, pharmacology and chemistry.

Verification: Applicants may be required to submit verification of qualifying education and experience at any point in the application and/or departmental selection process. Written verification (proof) of qualifying experience must verify that the applicant meets the minimum qualifications stated on the announcement. Written verification must be submitted on employer’s official letterhead, specifying name of employee, dates of employment, types of employment (part-time/full-time), job title(s), description of duties performed, and the verification must be signed by the employer. City employees will receive credit for the duties of the class to which they are appointed. Credit for experience obtained outside of the employee’s class will be allowed only if recorded in accordance with the provisions of the Civil Service Commission Rules. Experience claimed in self-employment must be supported by documents verifying income, earnings, business license and experience comparable to the minimum qualifications of the position. Copies of income tax papers or other documents listing occupations and total earnings must be submitted. If education verification is required, information on how to verify education requirements, including verifying foreign education credits or degree equivalency, can be found at http://sfdhr.org/index.aspx?page=456.

Desirable Qualifications:

• Understanding of data science, bioinformatics, computer science, or a related field.
• Experience in AI/ML modeling and data analysis with Python, SQL, and other data processing tools.
• Familiarity with mass spectrometry data, and experience in forensic toxicology or a related discipline.
• Understanding of LIMS systems, data pipelines, and workflow automation in laboratory environments.
• Interest in:
  • Development and Integration of AI/ML Infrastructure: Researching and designing infrastructure that supports AI/ML integration, including scalable data pipelines for efficient QTOF data management.
  • Identification of Positive Drugs in Untargeted Suspect Screening: Creating ML algorithms that enhance sensitivity and specificity in drug detection, reducing false positives and negatives.
  • Case Prediction Modeling: Developing predictive models that leverage case data to support forensic conclusions and optimize case management.
  • Data Management and Analysis: Ensuring smooth data flow within the LIMS and maintaining thorough documentation for reproducibility, validation, and regulatory adherence.
  • Research and Publication: Publishing findings in peer-reviewed journals, presenting at conferences, and staying current with advancements in forensic science, AI, and ML.