Principal Full Stack AI Engineer

Job Description

Position Summary

Vertex is seeking   a Full-Stack AI   Engineer to   help build, extend, and operate our   A gentic AI platform end to end. In this role you will develop AI agents and the services, APIs, and interfaces around them, and   connect the platform to the systems, tools, and data sources that make AI valuable in real enterprise workflows.

The ideal candidate   is a versatile engineer who is comfortable across the stack   including   backend services and APIs, agent frameworks and orchestration, data and retrieval pipelines, and lightweight front-end experiences   with real depth   in   enterprise integration design,   MCP/A2A protocols, event-driven architectures,   and   authentication patterns .   This individual will play a key role in ensuring AI capabilities are embedded into day-to-day work at Vertex   and   not as isolated proofs of concept, but as production-ready solutions integrated into the enterprise ecosystem.

Key Responsibilities

Platform and integrations: connecting the agentic AI platform to enterprise systems, third-party tools, and business-critical services through MCP, A2A, APIs, webhooks, and event-driven patterns

Agent and service development: building agents, tools, and the backend services that support tool use, orchestration, memory, and action execution

Data and retrieval: making structured and unstructured enterprise content usable by AI workflows through ingestion, retrieval, and grounding patterns

User-facing experiences: building and extending lightweight interfaces, chat surfaces, and developer-facing SDKs and connectors that put agents in the flow of work

Reliability and governance: observability, evaluation, security reviews, and the standards that keep agentic solutions safe and supportable in a regulated environment

Build and ship AI and agentic capabilities end to end, from backend services and APIs to the interfaces and connectors users and developers interact with

Design, build, and maintain integrations between the AI/agentic platform and enterprise systems, internal applications, third-party tools, and business services

Implement secure, scalable connectivity patterns that enable AI agents and workflows to access data, trigger actions, and interact with enterprise platforms

Develop and support integrations using MCP, A2A, APIs, webhooks, and event-driven architectures

Create reusable connectors, SDKs, middleware components, and service patterns that accelerate onboarding of new tools and systems into the AI platform

Implement agent capabilities such as tool use, orchestration, retrieval, and action execution, and tune them for accuracy, latency, and cost

Partner with platform, product, data, security, and enterprise application teams to ensure solutions meet technical, business, and compliance requirements

Design robust authentication and authorization patterns for AI services, including identity propagation, token handling, and access control

Enable AI workflows to interact reliably with core enterprise platforms such as collaboration tools, knowledge systems, workflow tools, and line-of-business applications

Build data and retrieval pipelines that make structured and unstructured sources usable by AI and agentic applications

Implement monitoring, logging, tracing, evaluation, error handling, and alerting across agents and integration services

Ensure solutions are resilient, maintainable, observable, and aligned with enterprise architecture standards

Contribute to platform governance by defining standards, documentation, onboarding guidance, and best practices

Troubleshoot and resolve issues related to connectivity, data exchange, authentication, latency, and downstream service dependencies

Evaluate emerging standards and tools in AI engineering, system interoperability, and enterprise integration to inform platform evolution

Required Qualifications

Bachelor's degree in Computer Science , Information Systems, Software Engineering, or a related technical field; equivalent practical experience may be considered

Experience in software engineering, AI/application engineering, or platform engineering, including shipping production services

Full-stack development experience in Python and/or TypeScript, spanning backend services and APIs plus modern front-end or developer-facing surfaces

Hands-on experience building with LLMs and agent frameworks, including tool calling, orchestration, retrieval-augmented generation, prompting, and evaluation

Strong hands-on experience designing and implementing API-based integrations in enterprise environments

Experience with MCP, A2A, service-to-service communication, or similar integration/interoperability patterns

Strong understanding of event-driven architecture, messaging systems, asynchronous processing, and workflow-based integration design

Experience with authentication and authorization standards such as OAuth, OIDC, SSO, service principals, secrets management, and token-based security

Familiarity with enterprise application integration patterns, middleware, and distributed systems design

Experience building secure, scalable, and reliable production services on modern cloud platforms

Strong problem-solving skills and ability to work across multiple systems, teams, and technical domains

Strong written and verbal communication skills with the ability to document and explain technical approaches clearly

Understanding of AI-native software engineering practices, including effective and responsible use of AI coding assistants and software engineering agents

Technical Skills

Python and/or TypeScript across backend and front-end

LLM APIs, agent frameworks, tool calling, and orchestration

Prompt design, evaluation harnesses, and quality/cost/latency tuning

Retrieval-augmented generation, embeddings, and vector stores

MCP and A2A protocols

REST APIs and service integration

Webhooks and event-driven integration patterns

Enterprise application integration

Authentication and authorization design

OAuth, OIDC, SSO, and token management

Distributed systems and microservices

Messaging and asynchronous processing

Observability, logging, tracing, and monitoring

Data exchange patterns across enterprise systems

Secure connectivity and secrets management

Cloud platforms and cloud-native architectures

Error handling, resiliency, and performance optimization

Versioning, testing, CI/CD, and deployment of production services

Preferred Skills

Experience building or integrating AI and agentic platforms with enterprise tools and business systems

Experience with Microsoft AI and cloud technologies such as Azure AI Foundry, M365 Copilot, and agent frameworks

Familiarity with workflow orchestration platforms and automation frameworks

Experience building reusable connectors or SDKs for platform extensibility

Knowledge of enterprise data platforms, document systems, knowledge repositories, and collaboration tools

Experience with regulated environments such as biotechnology, pharmaceuticals, healthcare, or life sciences

Experience supporting platform governance, security reviews, and technical documentation

Understanding of observability and evaluation practices for complex, multi-system agentic workflows

#LI-HYBRID

Pay Range:

$166,640 - $250,000

Disclosure Statement:

The range provided is based on what we believe is a reasonable estimate for the base salary pay range for this job at the time of posting. This role is eligible for an annual bonus and annual equity awards. Some roles may also be eligible for overtime pay, in accordance with federal and state requirements. Actual base salary pay will be based on a number of factors, including skills, competencies, experience, and other job-related factors permitted by law.

At Vertex, our Total Rewards offerings also include inclusive market-leading benefits to meet our employees wherever they are in their career, financial, family and wellbeing journey while providing flexibility and resources to support their growth and aspirations.  From medical, dental and vision benefits to generous paid time off (including a week-long company shutdown in the Summer and the Winter), educational assistance programs including student loan repayment, a generous commuting subsidy, matching charitable donations, 401(k) and so much more.

Flex Designation:

Hybrid-Eligible Or On-Site Eligible

Flex Eligibility Status:

In this Hybrid-Eligible role, you can choose to be designated as:

1.    Hybrid: work remotely up to two days per week; or select

2.    On-Site: work five days per week on-site with ad hoc flexibility.

Note: The Flex status for this position is subject to Vertex’s Policy on Flex @ Vertex Program and may be changed at any time.

#LI-Hybrid

Company Information

Vertex is a global biotechnology company that invests in scientific innovation.

Vertex is committed to equal employment opportunity and non-discrimination for all employees and qualified applicants without regard to a person's race, color, sex, gender identity or expression, age, religion, national origin, ancestry, ethnicity, disability, veteran status, genetic information, sexual orientation, marital status, or any characteristic protected under applicable law. Vertex is an E-Verify Employer in the United States. Vertex will make reasonable accommodations for qualified individuals with known disabilities, in accordance with applicable law.

Any applicant requiring an accommodation in connection with the hiring process and/or to perform the essential functions of the position for which the applicant has applied should make a request to the recruiter or hiring manager, or contact Talent Acquisition at ApplicationAssistance@vrtx.com