Senior Forward Deployed Engineer, AI Infrastructure & Deployments

About the role

You will own the end-to-end delivery of complex AI-native solutions within customer environments, bridging the gap between our platform and real-world enterprise requirements. This role requires a hands-on engineer to design, deploy, and maintain production systems while acting as a technical partner to our clients.

Key facts

What you'll do

• Architect and deploy AI-native solutions, including agentic workflows and MCP servers, into customer-specific cloud and data environments.
• Manage infrastructure using Terraform, focusing on AWS networking, IAM, security, and data isolation.
• Maintain and optimize data pipelines and integrations involving Databricks, Delta Lake, Snowflake, and S3.
• Lead technical engagements with customers, managing expectations, scoping requirements, and navigating compliance constraints.
• Develop reusable deployment patterns and engineering standards based on field experience to improve future delivery.

Requirements

• 7+ years of professional software engineering experience with a focus on production-grade systems.
• Hands-on experience building LLM-powered applications or agentic workflows using frameworks like LangGraph, Strands, or CrewAI.
• Advanced AWS and Terraform proficiency, specifically regarding VPC networking and security controls.
• Strong Python development skills, including experience with async patterns and API services.
• Experience managing large-scale data systems and debugging performance in production.
• Familiarity with enterprise compliance and security standards such as HIPAA, SOC 2, or BAA.
• Ability to lead technical discussions with stakeholders and translate complex requirements into actionable engineering plans.

Nice to have

• Experience with LLM evaluation tools like LangSmith, Braintrust, or Ragas.
• Domain knowledge in healthcare or life sciences, including IQVIA data or payer-provider workflows.
• Experience with service mesh or API gateway patterns for AI integration.
• Background in contributing to shared platform infrastructure or architecture governance.
• Experience with data residency, audit logging, and multi-party data access constraints.

Skills & tools

• Python, AWS, Terraform, Databricks, Delta Lake, Snowflake, S3, LangGraph, CrewAI, MCP (Model Context Protocol).

Practical notes

This role involves direct customer interaction and requires the ability to navigate ambiguous, regulated environments. You will be expected to own your work from initial architecture through to production outcomes.