Senior AI Software Engineer

About Us

Health Data Analytics Institute (HDAI) is a commercial-stage HealthTech company. Our Intelligent Health Management System, HealthVision™, is a first-in-class enterprise solution leveraging real-time predictive analytics and generative AI to deliver improved outcomes, efficiencies, and economics for health systems and value-based care organizations.

HDAI is located in Dedham, MA near the Dedham Corporate Center Commuter Rail station on the Franklin/Foxboro line (25 minutes from Back Bay and South Station, Boston) and I-95/128.

Summary

We are hiring a Senior AI Software Engineer to join our Product Engineering team. In this role, you will bridge the gap between Data Science and production software by owning our full AI/ML backend. This includes a high-throughput predictive inference engine (scoring 580+ patient risk models in real time) and generative LLM pipelines on Amazon Bedrock (powering clinical summaries and diagnostic discovery).

You will work across the entire backend stack as priorities shift, developing deep domain expertise while ensuring complete system coverage.

We expect you to use AI tools daily to multiply your output.

Responsibilities

• Inference engine. Own the system that scores patients against hundreds of predictive models in production. Understand the scaling concerns (580+ models, memory pressure, compute efficiency) and drive architectural improvements.

• ML productization. Work with Data Science to take model artifacts (coefficient files, scoring logic built in R) and ensure they run correctly in the production Python inference pipeline. Understand the underlying model logic and statistical outputs well enough to validate data and parity between the R development environment and production output. Build tooling that automates validation and reduces the manual reimplementation cycle.

• LLM applications. Build and maintain production LLM integrations on Amazon Bedrock (Claude) for AI summaries, PDD, and conversational interfaces. Manage prompt lifecycle: design, versioning, testing, and evaluation. Handle the specific challenges of LLM applications in production: token management, output validation, evidence citation, structured output parsing, and graceful degradation.

• Production AI engineering. Build and maintain production Python services on AWS (Lambda, DynamoDB, SQS, S3). Work across the existing stack including FastAPI and legacy services during migration to serverless.

• Evaluation and quality. Build testing and evaluation frameworks for both model inference and LLM outputs. Define what “correct” means for AI-generated clinical content in collaboration with Clinical and Data Science teams. Write tests for critical paths. Monitor production output quality and catch regressions.

• Cross-functional collaboration. Partner with Data Science on model release planning, validation, and new prompt development. Work with Platform Engineering on deployment infrastructure. Collaborate across the full Product Engineering team on features that span frontend and backend.

Qualifications

Required:

• 7+ years of experience as a software engineer, ML engineer, or AI engineer building production systems.

• Strong Python proficiency for production service development.

• Experience building and operating services on AWS (Lambda, API Gateway, DynamoDB, SQS, S3) or equivalent cloud platforms.

Experience in at least one of these areas, with willingness to grow into the other:

ML engineering: taking model artifacts from data science and deploying them to production. You understand model scoring, feature engineering, and what it takes to validate that a production implementation matches the original model.

LLM engineering: building production LLM applications (not just prototypes). You have worked with model APIs (Bedrock, OpenAI, or similar), designed prompt architectures, and handled the failure modes of generative AI in production.

• AI-native engineering practice. You use AI tools (Claude Code, Cursor, or similar) as a core part of your daily workflow.

• Comfort with ambiguity. Requirements evolve as we scale to new health system partners; you make sound decisions with incomplete information.

• Clear written and verbal communication.

Preferred:

• Experience across both ML engineering and LLM engineering (see above).

• Experience with Amazon Bedrock or similar managed LLM services.

• Experience with R or familiarity reading R code (our data science team works in R).

• Experience with model serving at scale (hundreds of models, multi-tenant environments).

• Healthcare or regulated industry experience.

• Experience building evaluation/testing frameworks for AI system outputs.

• Experience with FastAPI, event-driven architectures (SQS, SNS), or serverless patterns.

• Familiarity with Terraform and infrastructure-as-code.

Equal Opportunity

HDAI is committed to creating a diverse environment and is proud to be an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.