Software Engineer, AI Platform

Bask Health

About The Position

Bask Health is seeking a Software Engineer, AI Platform to build and maintain foundational infrastructure for AI-powered applications across its telehealth software platform. The role focuses on reusable APIs, model integration services, inference gateways, data access components, and operational tools that enable engineering teams to build and deploy AI capabilities efficiently across merchant tools, patient experiences, clinical workflows, pharmacy operations, and internal systems. The engineer will work with backend technologies, cloud infrastructure, databases, model providers, and distributed systems to develop scalable services for AI requests and application resources. Work may include centralized model access, request routing, usage tracking, authentication, rate limiting, prompt configuration, observability, and infrastructure for retrieval and agent-based applications. The role collaborates with applied AI, machine learning, product, and infrastructure engineers to identify shared technical needs and build reusable platform capabilities. Because Bask operates in healthcare-related environments, the engineer will help ensure infrastructure respects privacy requirements, tenant isolation, access controls, and approved data-handling practices. This hands-on role owns production infrastructure and shared developer capabilities, including writing code, improving architecture, investigating operational issues, and establishing patterns that support reliable, secure, and maintainable AI integrations. Bask describes its engineering approach as AI-first and builder-led, using tools such as Cursor and Claude Code while maintaining standards for reliability, testing, and software quality.

Requirements

At least 3 years of professional software engineering experience, preferably in backend, platform, or infrastructure engineering.
Demonstrated experience building and maintaining production backend services.
Strong programming skills in TypeScript, JavaScript, Python, or comparable backend languages.
Experience designing and developing APIs and service integrations.
Strong understanding of backend application architecture and distributed systems fundamentals.
Familiarity with large language models and modern AI application integration patterns.
Experience integrating third-party APIs or external services into production applications.
Understanding of authentication, authorization, and secure service communication.
Experience working with relational databases and application data models.
Familiarity with asynchronous processing, background jobs, and event-driven systems.
Experience designing systems that handle errors, retries, timeouts, and service failures.
Understanding of cloud infrastructure and production deployment practices.
Familiarity with automated testing and continuous integration workflows.
Experience with logging, monitoring, and production observability tools.
Understanding of system performance, latency, scalability, and reliability.
Experience designing reusable software components and shared engineering services.
Familiarity with API versioning, configuration management, and service maintenance.
Understanding of data privacy and secure application development.
Experience using Git, code review, and collaborative software development practices.
Ability to troubleshoot complex backend and infrastructure issues.
Experience writing maintainable, well-documented production code.
Ability to evaluate engineering tradeoffs involving performance, complexity, and operational costs.
Experience collaborating with engineers across multiple product or technical teams.
Strong technical problem-solving and analytical skills.
Ability to independently own engineering projects from design through deployment.

Nice To Haves

Experience building infrastructure for AI or machine learning applications.
Familiarity with OpenAI, Anthropic, or comparable model APIs.
Experience building model gateways, inference proxies, or centralized AI integration services.
Familiarity with multi-model routing and provider fallback strategies.
Experience with TypeScript and Node.js backend development.
Familiarity with tRPC, Prisma, Drizzle, or similar application development tools.
Experience with AWS Lambda, SQS, EventBridge, or comparable cloud services.
Familiarity with serverless infrastructure and infrastructure-as-code tools.
Experience with SST or similar application deployment frameworks.
Familiarity with containerization and distributed service deployment.
Experience building systems for API rate limiting, usage metering, or cost allocation.
Familiarity with embeddings, vector databases, and retrieval infrastructure.
Experience supporting retrieval-augmented generation applications.
Experience building shared infrastructure for AI agents or automated workflows.
Familiarity with prompt management, versioning, and configuration systems.
Experience implementing AI request tracing and model observability.
Experience developing internal SDKs, libraries, or developer platforms.
Understanding of multi-tenant SaaS architecture and data isolation.
Familiarity with HIPAA and healthcare data privacy considerations.
Experience using AI-assisted development tools such as Cursor or Claude Code.

Responsibilities

Design, build, and maintain shared infrastructure for AI-powered applications across Bask Health.
Develop backend services and APIs for model integration and AI application execution.
Build reusable components for consistent access to large language models.
Develop centralized model integration services and inference request handling.
Implement routing and configuration for multiple model providers.
Build systems for managing model API credentials, authentication, and access permissions.
Develop request validation, structured output handling, and standardized error responses.
Implement rate limiting, retries, timeouts, and fallback mechanisms for model API requests.
Build usage tracking and cost monitoring for AI services.
Develop infrastructure for prompt configuration, versioning, and controlled updates.
Create shared services for embeddings, retrieval, and knowledge-grounded AI applications.
Build APIs and integration patterns for AI agents and workflow automation.
Develop secure data access components for AI applications.
Ensure AI services respect tenant boundaries and application authorization requirements.
Build observability for model requests, latency, errors, and operational performance.
Implement structured logging and distributed tracing across AI services.
Develop automated testing and deployment pipelines for AI platform components.
Improve infrastructure reliability, fault tolerance, and service availability.
Optimize backend performance, throughput, and infrastructure costs.
Design scalable asynchronous processing and background job systems.
Integrate AI platform services with existing application databases and backend infrastructure.
Build internal developer tools and documentation to simplify AI application development.
Collaborate with applied AI engineers to identify common infrastructure needs.
Support machine learning engineers with reliable model-serving and evaluation integrations.
Investigate production incidents and resolve infrastructure-related failures.
Participate in architecture discussions, technical planning, and code reviews.
Establish reusable engineering patterns for secure and maintainable AI integrations.
Own assigned platform services from technical design through deployment, monitoring, and continuous improvement.