Senior Ai Engineer
Job Description
Health Data Analytics Institute (HDAI) is hiring a Senior AI Software Engineer to build and operate production AI systems at the backend of real healthcare workflows. This hybrid role in Dedham, MA focuses on high-throughput predictive inference, production LLM integrations on Amazon Bedrock, and the testing and monitoring needed to keep AI outputs reliable. Compensation is USD 160,367 - 185,457 per year.
What you will work on
You will own the AI/ML backend end to end, acting as the bridge between Data Science and production software engineering. The work includes running patient scoring against hundreds of predictive models in production and building production-grade LLM capabilities for clinical-facing content, including summary and conversational experiences.
- Own the system that scores patients against 580+ predictive models in production, while driving architectural improvements for scaling concerns like memory pressure and compute efficiency.
- Partner with Data Science to take model artifacts (such as coefficient files and scoring logic built in R) and ensure they run correctly in the production Python inference pipeline, including validating data and parity between the R development environment and production outputs.
- Build tooling that automates validation so model behavior remains consistent as systems evolve.
- Build and maintain production LLM integrations on Amazon Bedrock (Claude) for AI summaries, PDD, and conversational interfaces, including prompt lifecycle management (design, versioning, testing, and evaluation).
- Handle production realities for generative AI such as token management, output validation, evidence citation, structured output parsing, and graceful degradation.
- Build and maintain production Python services on AWS using Lambda, DynamoDB, SQS, and S3, working 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, in collaboration with Clinical and Data Science teams to define what “correct” means for AI-generated clinical content.
- Write tests for critical paths, monitor production output quality, and catch regressions early.
- Collaborate on model release planning, validation, and new prompt development with Data Science, and coordinate with Platform Engineering on deployment infrastructure.
- Work across the full Product Engineering team on features spanning frontend and backend.
Requirements
- 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 an equivalent cloud platform.
- Experience deploying model artifacts from Data Science into production, including understanding model scoring and feature engineering, and validating production parity with the original model.
- Experience building production LLM applications (not only prototypes), using model APIs (Bedrock, OpenAI, or similar), designing prompt architectures, and handling generative AI failure modes in production.
- Use AI tools (such as Claude Code and Cursor) as a core part of daily workflow.
- Comfort with ambiguity and making sound decisions as requirements evolve.
- Clear written and verbal communication.
Technologies
Python, AWS, Amazon Bedrock, Claude, Lambda, DynamoDB, SQS, S3, API Gateway, FastAPI, R, Claude Code, Cursor
Benefits
- 401(k)
- 401(k) matching
- Dental insurance
- Health insurance
- Health savings account
- Paid time off
- Retirement plan
- Tuition reimbursement
- Vision insurance
Preferred
- 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.
- Experience with model serving at scale (hundreds of models, multi-tenant environments).
- Healthcare or regulated industry experience.
- Experience building evaluation and testing frameworks for AI system outputs.
- Experience with FastAPI, event-driven architectures (SQS, SNS), or serverless patterns.
- Familiarity with Terraform and infrastructure-as-code.