Scientific AI Engineer — Immunology Data Systems

Harvard Medical School; Boston (MA); On-site; USD 130,000 - 170,000; Full time

Benefits offered by this job

Parental leave

Medical, dental, and vision coverage

Retirement plans with universitycon-

Wellbeing resources

Support for families and caregivers

Tuition assistance and reimbursement

Commuter benefits

Job summary

Harvard Medical School's ImmGen program seeks a Scientific AI Engineer to design an AI-powered data agent that leverages ImmGen data with external resources to answer scientists’ questions in natural language. You will wrap and orchestrate existing tools, define use cases, and ensure robust, reproducible results.

The role emphasizes safe, cost-conscious AI workflows, collaboration with immunology researchers, and developing interfaces to connect data resources to an AI agent.

Qualifications

• Minimum of five years’ post-secondary education or relevant work experience.
• Advanced degree or equivalent professional experience in computational biology, bioinformatics, genomics, or a related field.
• Strong Python programming skills and experience with scientific computing libraries such as pandas, NumPy, SciPy, scikit-learn, Scanpy, Bioconductor, or equivalent tools.
• Strong software-engineering skills, including experience with APIs, data schemas, testing, version control, logging, documentation, and reproducible workflows.
• Experience integrating software with existing scientific data platforms, analytical pipelines, web services, or computational tools.
• Hands-on experience with LLM applications, including tool/function calling, retrieval-augmented generation, structured outputs, agent orchestration, or natural-language-to-SQL/code systems.

Responsibilities

• Work closely with ImmGen scientists to understand datasets, metadata, tools, APIs, and access mechanisms.
• Wrap existing ImmGen data so they can be invoked by an LLM-based agent.
• Collaborate to define use cases, formats, and scientific language and graphics.
• Map questions to ImmGen resources and workflows.
• Develop interfaces, schemas, guardrails and orchestration logic to connect the agent to ImmGen infrastructure.
• Implement safeguards against hallucinations, invalid interpretations and unsupported claims.
• Ensure that expensive computes are not triggered automatically.
• Be a team player in rewriting scientific data propagation.

Skills

Python

LLM applications

Education

Advanced degree in computational biology

Tools

APIs

Data schemas

Testing

Version control

Logging

Documentation

Reproducible workflows

Job description

Harvard Medical School's ImmGen program seeks a Scientific AI Engineer to design an AI-powered data agent that leverages ImmGen data with external resources to answer scientists’ questions in natural language. You will wrap and orchestrate existing tools, define use cases, and ensure robust, reproducible results.

The role emphasizes safe, cost-conscious AI workflows, collaboration with immunology researchers, and developing interfaces to connect data resources to an AI agent.