Senior AI Software Engineer

Senior AI Software Engineer role on the Product Engineering team, focused on production AI/ML backend systems and Amazon Bedrock LLM pipelines.

Responsibilities

• Own the production patient scoring system using hundreds of predictive models (580+ models), with attention to memory pressure and compute efficiency.
• Partner with Data Science to operationalize model artifacts (coefficient files and scoring logic implemented in R) into a production Python inference pipeline.
• Validate input data and ensure parity between the R development environment and production outputs.
• Build tooling to automate validation and reduce manual reimplementation when moving from development to production.
• 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.
• Handle LLM production concerns such as token management, output validation, evidence citation, structured output parsing, and graceful degradation.
• Develop and maintain production Python services on AWS using Lambda, DynamoDB, SQS, and S3, working across FastAPI and legacy services during migration to serverless.
• Create testing and evaluation frameworks for both model inference and LLM outputs, defining what “correct” means for clinical content with Clinical and Data Science teams.
• Write tests for critical paths and monitor production output quality to detect regressions.
• Collaborate with Platform Engineering on deployment infrastructure and coordinate with the full Product Engineering team on features spanning frontend and backend.
• Support Data Science on model release planning, validation, and prompt development.

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 (or equivalent cloud), including Lambda, API Gateway, DynamoDB, SQS, S3.
• Experience in at least one area, with willingness to grow into the other:
  • ML engineering: deploy model artifacts from Data Science, including model scoring, feature engineering, and validation that production matches the original model.
  • LLM engineering: build production LLM applications (not prototypes), work with model APIs such as Bedrock or OpenAI, design prompt architectures, and handle generative AI failure modes in production.
• AI-native engineering practice: use AI tools such as Claude Code or Cursor as a core part of daily workflow.
• Comfort with ambiguity as requirements evolve with new health system partners and scaling decisions are made with incomplete information.
• Clear written and verbal communication.

Technologies

• Python
• AWS, Lambda, API Gateway, DynamoDB, SQS, S3
• FastAPI
• Amazon Bedrock, Claude
• R
• Terraform (infrastructure-as-code)
• Claude Code, Cursor
• OpenAI

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 (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.

Location: Dedham, MA (hybrid). Compensation: USD 160,367 - 185,457 per year. Minimum experience: 7 years.