Senior AI Software Engineer

Health Data Analytics Institute is hiring a Senior AI Software Engineer to join the Product Engineering team in Dedham, MA (hybrid). In this role, you will help power production-ready AI systems, from predictive scoring at scale to production LLM pipelines on Amazon Bedrock, supporting clinical and health data workflows end to end.

What you’ll work on

• Own the AI/ML backend that performs production predictive inference, including a system that scores patients against hundreds of predictive models and addresses scaling concerns such as memory pressure and compute efficiency (including environments with 580+ models).
• Partner with Data Science to take model artifacts (such as coefficient files and scoring logic implemented in R) and ensure they execute correctly in a production Python inference pipeline. Validate data handling and parity between the R development environment and production output, and build tooling that automates validation to reduce manual reimplementation.
• Build and maintain production LLM integrations on Amazon Bedrock (Claude) for AI summaries, PDD, and conversational interfaces. Manage the prompt lifecycle, including design, versioning, testing, and evaluation, while handling token management, output validation, evidence citation, structured output parsing, and graceful degradation.
• Develop and maintain production Python services on AWS, working with Lambda, DynamoDB, SQS, and S3, and collaborating across the existing stack including FastAPI and legacy services during migration to serverless.
• Create testing and evaluation frameworks for both model inference and LLM outputs. Define what “correct” means for AI-generated clinical content with Clinical and Data Science teams, write tests for critical paths, and monitor production output quality to catch regressions.
• Support model release planning with Data Science, collaborate with Platform Engineering on deployment infrastructure, and work across Product Engineering for features spanning frontend and backend.

What you bring

• 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 (or equivalent cloud), including Lambda, API Gateway, DynamoDB, SQS, and S3.
• Experience in at least one: ML engineering (deploying model artifacts from Data Science to production, understanding scoring and feature engineering, and validating production parity with the original model), with willingness to grow into the other area.
• Experience in at least one: LLM engineering (building production LLM applications beyond prototypes, working with model APIs such as Bedrock or OpenAI, designing prompt architectures, and handling generative AI failure modes), with willingness to grow into the other area.
• AI-native engineering practice: using AI tools (such as Claude Code or Cursor) as a core part of the daily workflow.
• Comfort with ambiguity as requirements evolve while scaling to new health system partners.
• Clear written and verbal communication.

Tools you’ll use

Python, AWS, Lambda, API Gateway, DynamoDB, SQS, S3, FastAPI, Amazon Bedrock, Claude, R, Terraform, Claude Code, Cursor, OpenAI

Compensation and benefits

Salary: USD 160,367 - 185,457 per year. Schedule: hybrid in Dedham, MA. Experience level: 7+ years.

• 401(k)
• 401(k) matching
• Dental insurance
• Health insurance
• Health savings account
• Paid time off
• Retirement plan
• Tuition reimbursement
• Vision insurance

Preferred qualifications

• Experience across both ML engineering and LLM engineering.
• Experience with Amazon Bedrock or similar managed LLM services.
• Experience with R or familiarity reading R code (Data Science 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.