Senior AI Platform Engineer

*About the Company *

Our client is a rapidly growing, AI-native healthcare technology company building production AI systems that automate some of the most complex and operationally important workflows in healthcare.

The platform applies artificial intelligence to medical coding, clinical documentation review, revenue cycle management, healthcare data processing, and other workflows that have historically required significant manual effort.

AI is the core product—not an experimental feature or an add-on to an existing software platform. The systems being built are customer-facing, production-critical, and directly connected to healthcare organizations’ operational and financial performance.

Because the platform processes complex clinical and administrative information, the engineering team must build AI systems with exceptionally high standards for accuracy, reliability, explainability, security, and performance.

As the company continues to scale, it is investing heavily in the AI engineering foundations required to support larger customers, increasingly complex healthcare workflows, and a growing volume of unstructured clinical and financial data.

For experienced AI engineers who enjoy owning architecture, solving difficult backend AI problems, and seeing their work directly influence customer outcomes, this is an opportunity to help shape both the product and the long-term technical direction of an AI-native healthcare company.

*What You’ll Be Working On *

The engineering organization builds production AI systems that analyze healthcare information, automate operational workflows, and support high-stakes decisions across clinical and financial environments.

As a Senior AI Engineer, you will help design and improve systems involving:

• Production LLM applications used by healthcare organizations
• Retrieval-Augmented Generation systems operating across complex document collections
• Clinical documentation review and medical coding workflows
• Large-scale document processing, classification, and information extraction
• Semantic search and enterprise healthcare knowledge systems
• Multi-agent and agentic AI workflows
• LLM orchestration, routing, and tool-use systems
• Model evaluation, hallucination reduction, and quality measurement
• Model monitoring, drift detection, and continuous performance improvement
• Backend APIs and distributed services supporting customer-facing AI products
• Event-driven workflows processing healthcare data at production scale
• AI observability, reliability, latency, and cost optimization

Much of the platform already operates in production today. The next phase is focused on improving retrieval quality, expanding automation capabilities, strengthening production reliability, and building the technical foundations required to support continued customer growth.

*About the Role *

Our client is hiring a Senior AI Engineer to design, build, deploy, and operate customer-facing AI systems from initial architecture through long-term production support.

This is a deeply hands-on engineering position for someone who enjoys solving complex backend AI problems, making architectural decisions, and taking ownership of AI initiatives from concept through production.

You will work across LLM applications, document intelligence, retrieval systems, agentic workflows, backend services, model evaluation, and production infrastructure. Rather than focusing exclusively on experimentation or model research, you will be responsible for building AI systems that customers depend on every day.

The ideal candidate has personally owned production AI architecture, deployed systems into real customer environments, improved those systems after launch, and made thoughtful technical tradeoffs involving accuracy, latency, cost, scalability, reliability, and maintainability.

Our client is looking for builders—not researchers.

*What You Will Do *

• Design the architecture for customer-facing AI products, LLM applications, retrieval systems, and document-processing workflows
• Lead AI initiatives from early technical discovery through implementation, deployment, monitoring, and continuous production improvement
• Build production Retrieval-Augmented Generation systems across large collections of clinical, financial, and operational documents
• Develop document understanding pipelines involving information extraction, semantic search, classification, OCR, and structured data generation
• Design multi-agent and agentic workflows that can reason across documents, call tools, coordinate tasks, and complete complex healthcare processes
• Build and maintain Python-based backend services and APIs supporting production AI capabilities
• Develop distributed and event-driven systems using cloud infrastructure, queues, containers, serverless services, and asynchronous processing
• Determine when to use prompting, retrieval, fine-tuning, deterministic workflows, or agentic architectures
• Evaluate architectural tradeoffs between model quality, latency, infrastructure cost, scalability, explainability, and maintainability
• Create model evaluation frameworks that measure accuracy, retrieval quality, hallucination rates, consistency, and task completion
• Implement production monitoring, AI observability, drift detection, tracing, and failure analysis
• Identify and resolve production issues involving models, retrieval pipelines, prompts, data quality, orchestration, and backend infrastructure
• Improve existing AI systems through prompt optimization, context engineering, retrieval tuning, model selection, fine-tuning, and architectural changes
• Optimize inference latency, token consumption, cloud costs, retrieval performance, and system throughput
• Build safeguards and validation layers that increase the reliability of AI-generated outputs
• Partner closely with Product, Engineering, Operations, and Executive Leadership to translate healthcare problems into scalable technical solutions
• Communicate architecture decisions, technical risks, and engineering tradeoffs clearly to both technical and nontechnical stakeholders
• Identify important technical problems before they are formally assigned and take ownership of solving them
• Help establish reusable AI engineering patterns, technical standards, and development practices as the organization grows

*What Our Client Is Looking For *

• Strong software engineering experience building production applications and backend systems
• Advanced Python development experience
• Experience developing backend APIs using FastAPI or similar frameworks
• Hands-on experience designing, deploying, and supporting production LLM applications
• Strong experience with Retrieval-Augmented Generation, semantic retrieval, and vector search
• Experience building systems involving NLP, document understanding, or unstructured data
• Experience with multi-agent systems, agentic workflows, or LLM tool-use architectures
• Experience using LLM orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or similar technologies
• Understanding of prompt engineering, context engineering, structured generation, and LLM output validation
• Experience building model evaluation frameworks and measuring AI system quality
• Experience reducing hallucinations and improving the accuracy of production AI outputs
• Experience implementing model monitoring, drift detection, tracing, or AI observability
• Understanding of fine-tuning strategies such as LoRA, QLoRA, or equivalent approaches
• Experience working with vector databases such as Pinecone, Milvus, Weaviate, FAISS, Chroma, or similar technologies
• Experience designing distributed systems and event-driven architectures
• Strong cloud engineering experience, preferably with AWS
• Experience with services such as Bedrock, SageMaker, ECS, Lambda, SQS, or comparable cloud technologies
• Ability to independently make architecture decisions and explain the reasoning behind technical tradeoffs
• Experience operating AI systems after launch rather than handing them off after initial deployment
• Strong communication skills and the ability to collaborate across Product, Engineering, Operations, and Leadership
• Startup, scale-up, or high-growth technology company experience preferred

*Senior-Level Expectations *

• You have personally designed and deployed production AI systems used by real customers
• You have owned AI initiatives from architecture through implementation, launch, monitoring, and continued improvement
• You can independently translate an ambiguous business problem into a scalable AI and backend architecture
• You understand that a successful AI product requires more than selecting a model or writing prompts
• You have improved retrieval quality, reduced hallucinations, optimized latency, or increased model reliability in a production environment
• You can identify whether a problem is best solved through prompting, RAG, fine-tuning, agentic workflows, traditional software, or a combination of approaches
• You make thoughtful tradeoffs between accuracy, cost, latency, scalability, explainability, and maintainability
• You remain deeply hands-on while influencing broader AI architecture and engineering direction
• You proactively identify technical risks and opportunities rather than waiting for detailed assignments
• You are comfortable operating in an environment where requirements may evolve as the product and customer base grow
• You think beyond models and frameworks and understand how technical decisions affect customers, product quality, and business performance
• You can clearly communicate complex AI concepts and architecture decisions to technical and nontechnical stakeholders

*Modern AI Engineering Approach *

• Strong software engineering fundamentals and a production-first engineering mindset
• Builder mentality with an emphasis on shipping dependable customer-facing systems
• Pragmatic approach to choosing models, frameworks, infrastructure, and architectural patterns
• Ability to combine deterministic software with probabilistic AI systems
• Strong understanding of evaluation-driven AI development
• Comfortable creating automated testing and validation systems for nondeterministic AI outputs
• Experience incorporating human review, confidence scoring, escalation paths, or validation layers when appropriate
• Ability to automate repetitive model evaluation, prompt testing, and production analysis
• Comfortable working across AI applications, backend services, cloud infrastructure, and product workflows
• Product-oriented thinking with the ability to connect AI performance to customer and business outcomes
• Willingness to challenge unnecessary complexity and use the simplest architecture capable of reliably solving the problem

*Nice to Have *

• Healthcare technology experience
• Experience building AI products for healthcare organizations, providers, payers, or revenue cycle teams
• Revenue Cycle Management experience
• Medical coding or clinical documentation experience
• Healthcare claims processing experience
• Clinical NLP experience
• Experience working with EHR data or healthcare interoperability standards
• Familiarity with FHIR, HL7, or healthcare integration environments
• Understanding of HIPAA requirements and healthcare data security
• Experience building automated healthcare workflows
• Experience processing large volumes of clinical or administrative documents
• OCR pipeline development experience
• Experience with enterprise search or knowledge management platforms
• Experience building AI systems in another highly regulated environment
• Experience at an AI infrastructure company, healthcare AI company, or high-growth technology startup
• Experience introducing evaluation, observability, or reliability standards to a growing AI engineering organization
• Experience improving an existing production AI platform rather than only building greenfield prototypes

Healthcare experience is strongly preferred, but it is not an absolute requirement. Engineers from other industries should be considered when they have demonstrated strong ownership of high-quality, customer-facing AI systems operating at meaningful production scale.

*This Role Is Not a Fit If *

• Your experience has primarily focused on AI or machine learning research
• Your background is primarily in data science without significant software engineering ownership
• You have mainly built notebooks, demonstrations, or internal proofs of concept
• You have not personally deployed AI systems into customer-facing production environments
• Your experience is centered on prompt engineering without backend engineering or systems architecture
• You prefer experimentation and model development over operating production systems
• You have trained models but have limited experience building the surrounding APIs, infrastructure, evaluation, and monitoring systems
• You prefer receiving fully defined technical requirements before beginning work
• You are looking for a narrowly scoped role focused on only one model, framework, or component
• You prefer highly structured environments with multiple layers of technical approval
• You are uncomfortable making independent architecture decisions in ambiguous situations
• You are primarily interested in publishing research rather than building commercial AI products
• You consider an AI project complete once the first version has been deployed
• You have not been responsible for improving the reliability, accuracy, latency, or cost of an AI system after launch

*Compensation and Benefits *

Base salary: $130,000–$180,000 USD, depending on experience and impact

Additional compensation

Competitive equity package; additional benefits and compensation details will be discussed during the interview process

*Why This Role Matters *

Artificial intelligence is changing how healthcare organizations process information, manage documentation, protect revenue, and operate complex administrative workflows.

However, building AI systems for healthcare requires significantly more than connecting an application to a language model. These systems must process difficult and inconsistent documents, generate dependable outputs, integrate with existing workflows, and perform reliably in production environments where mistakes can create meaningful financial and operational consequences.

This role will have direct influence over how the company’s AI systems are designed, evaluated, deployed, monitored, and improved.

This Senior AI Engineer will help determine the architecture behind customer-facing AI products, establish engineering standards for production AI development, and build systems that automate work traditionally performed through time-consuming manual processes.

This is an opportunity to take meaningful ownership at an AI-native company where artificial intelligence is the product, technical decisions are closely connected to customer outcomes, and the engineer’s work will be visible across the entire organization.

For someone who enjoys building production AI systems, solving complex document and backend engineering problems, and owning technical initiatives from concept through long-term operation, this role offers the opportunity to make an immediate and lasting impact.