Principal AI Engineer

DRFIRST COM INC• US,

12d•$150,000 - $200,000•Remote

About The Position

DrFirst is building an agentic ecosystem and has already shipped production AI systems across HR, Finance, Legal, and Marketing. This hands-on technical leadership role architects and builds production AI automation systems from discovery through deployment, working directly with department leaders to map workflows and deliver tools that augment their work. The role is approximately 80% individual-contributor engineering and 20% servant leadership and mentorship. The engineer owns technical architecture decisions and will mentor a team expected to grow from 2 to 5–6 engineers over 18 months, while keeping hands-on building as the primary focus. The position implements department sprints by building Python/FastAPI backends, Next.js/React frontends, multi-agent systems, and integrations with enterprise platforms. It also addresses enterprise networking and infrastructure, testing, deployment, performance, security, and production support. The role ships several production tools in parallel and may deploy multiple times per day in response to stakeholder feedback. The leadership component includes guiding 2–3 engineers through code reviews and pairing, teaching department leaders to use AI tools, translating technical decisions for executives, running workflow discovery sessions, removing blockers, and documenting reusable patterns. There are no direct reports or performance reviews. Daily work includes coordination with the VP of AI Automation and stakeholders, discovery sessions, coding, security reviews with the CISO, production support, and code reviews. DrFirst is a remote-first company. The role is primarily desk-based, with occasional travel. Compensation is a base salary of $150,000–$200,000, with exact compensation potentially varying based on skills and experience.

Requirements

At least 8 years building production systems end-to-end across backend, frontend, integrations, and infrastructure.
Staff/Principal Engineer or Tech Lead experience, including ownership of technical decisions on production systems.
Experience shipping SaaS products with OAuth2, multi-tenancy, audit trails, and enterprise compliance.
Deep AI/ML experience building production systems with LLM APIs such as OpenAI, Anthropic, or AWS Bedrock and agent frameworks.
Production Python experience with FastAPI, Pydantic, httpx, and pytest, including experience with a 1,000+ test suite.
Production TypeScript/React experience with Next.js App Router, server components, Okta/NextAuth SSO, and Playwright testing.
AWS and Kubernetes experience, including EKS operations, GitLab CI/CD, ArgoCD, Helm, and Secrets Manager.
Experience with enterprise security patterns including Zscaler proxies, SSL certificates, Kubernetes networking, and JWKS verification.
Healthcare or regulated-industry experience involving HIPAA, SOC 2, or similar frameworks.
Strong communication skills, including leading discovery sessions with non-technical stakeholders, explaining security trade-offs to executives, and writing architecture documentation for department leaders.
Servant leadership mindset, with a focus on removing blockers, teaching through questions rather than directives, and helping stakeholders succeed.
Ability to thrive in a fast-moving environment with many stakeholders, systems, and concurrent sprints.
Bias toward shipping work and getting feedback rather than waiting for perfection.
Collaborative approach, including constructively challenging ideas and welcoming feedback.
Active daily use of AI engineering tools such as Claude Code, GitHub Copilot, Cursor, Windsurf, or Cline.
At least one automation built that eliminated hours of manual work, ideally using LLM APIs.
Comfort teaching others to use AI tools through pairing and code review.

Nice To Haves

Experience leading small teams of 2–5 people through technical mentorship or tech lead roles.
US-based; US Central time zone preferred. Poland is also considered.
Experience building agentic systems, including agent coordination, scheduled routines, and feedback loops.
MCP (Model Context Protocol) experience, including custom connectors for enterprise systems.
Active contribution to AI/ML communities through papers, open source, or conference talks.
Strong code review, pairing, and documentation skills.
Experience teaching non-technical users through workshops, training, and business-user documentation.
Experience with Claude, including Claude.ai, Claude Code CLI, API integration, or AWS Bedrock; Claude experience is highly valued.

Responsibilities

Architect and implement production AI automation systems from workflow discovery through deployment.
Design and build Python/FastAPI backend services that integrate with enterprise APIs and systems.
Build Next.js/React frontends with Okta SSO, role-based access control, and audit trails.
Design multi-agent coordination systems, skill discovery hubs, agent registries, and workflow orchestration.
Integrate and troubleshoot enterprise systems and infrastructure, including proxies, VPNs, SSL certificates, Kubernetes networking, DynamoDB, and AWS Bedrock.
Write Playwright end-to-end tests and maintain a test suite with visual regression baselines.
Deploy using GitLab CI/CD to AWS EKS with Kubernetes, ArgoCD, Helm, and Secrets Manager; diagnose deployment and pod health issues.
Debug asynchronous and performance problems, including event-loop blocking and CPU-bound operations.
Partner with the CISO on PII/PHI de-identification, least privilege, and per-user OAuth2 security.
Support production systems by troubleshooting authentication, token expiration, API rate limits, and health-check failures.
Ship multiple production tools in parallel and deploy frequently based on stakeholder feedback.
Guide 2–3 engineers through code reviews, pairing, and help with complex integrations.
Run discovery sessions with department leaders to map workflows and teach non-technical leaders to use AI tools effectively.
Explain technical and security decisions to non-technical executives and stakeholders.
Remove blockers, escalate infrastructure issues, and coordinate work across departments.
Document reusable engineering patterns and create playbooks department heads can use independently.
Coordinate with the VP of AI Automation, stakeholders, and the CISO; participate in daily syncs, coding, security reviews, and production support.

Benefits

Competitive base salary of $150,000–$200,000; exact compensation may vary based on skills and experience.
Eligible for a company performance-based bonus program based on individual and company performance.
Medical, dental, and vision insurance.
401(k) eligibility after 3 months, with a 50% company match on the first 5% of salary contributed and a 3-year vesting schedule.
HSA for eligible employees enrolled in the HDHP, with company contributions up to $500 annually for individual coverage or $1,000 for family coverage.
Company-paid short- and long-term disability, AD&D, and group life insurance.
Accrued PTO: 18 days annually for the first 3 years of service, increasing thereafter.
7 paid holidays.
Employee Assistance Program.
Continuing education funds up to $1,500 annually for eligible programs after 1 year of service.
Voluntary benefits including FSA, hospital indemnity, accident, and critical illness insurance.