Principal AI Engineer

About DrFirst

For 25 years, DrFirst has empowered providers and patients to achieve better health through intelligent medication management. We improve healthcare workflows and help patients start and stay on therapy with end-to-end solutions that enhance prescription access, affordability, and adherence. Our solutions help 100 million patients a year and are used by more than 420,000 prescribers, 71,000 pharmacies, 270 EHRs and health information systems, and over 2,000 hospitals in the U.S. This is a great opportunity to be a part of a successful Healthcare IT company experiencing significant growth. Here you'll get to work with some of the smartest and most interesting people around; solving unique and complex challenges in healthcare on a scale matched by a few companies. If you get excited about stretching yourself in new ways, developing yourself to your fullest potential, care about working with smart colleagues; we want to talk to you!
Position Overview
DrFirst is building an agentic ecosystem at scale. In the last 90 days we have shipped production AI systems across HR, Finance, Legal, and Marketing, automating hundreds of hours of manual work monthly and delivering measurable business impact.
This is a hands-on technical leadership role. You architect and build production AI automation systems from discovery to deployment. You work directly with department leaders to map workflows and ship tools that augment their work.
The split is 80% individual-contributor engineering and 20% servant leadership and mentorship. You build. You own technical architecture decisions. As the team scales from 2 to 5-6 engineers over 18 months, you mentor through code review and pairing. You also teach non-technical department leaders how to use AI tools, translate technical concepts for executives, and run discovery sessions that extract workflows from stakeholders. Building stays your primary focus.
Who Will Love This Job

• You are a senior IC who loves shipping code daily. You have been a Staff or Principal Engineer or led small teams, but you miss hands-on building.

• You can architect multi-agent systems and run discovery sessions with department VPs to map their workflows.

• You can debug OAuth2 flows through enterprise proxies and explain security requirements to non-technical stakeholders.

• You are a servant leader. You remove blockers for others, teach through pairing rather than directives, and make stakeholders successful.

• You organize chaos: 15 stakeholders, 6 systems, 3 sprints in flight. You ask “How can I help?” before “Here is what you should do.”

What you will work on
Build Production AI Automation (80%)
You own the technical implementation of department sprints. Example: an HR sprint delivered resume screening (40-candidate PDF extraction with table-of-contents parsing and fuzzy name matching), OKR coaching (Leapsome API integration with performance rating analytics), performance ratings (calibration detection across 328 employees), and milestone email automation in 4 weeks.

• Architecture and Implementation: Design and build Python/FastAPI backends connecting to enterprise APIs (HRIS, ERP, CRM, finance systems, project management).

• Frontend Development: Build Next.js/React frontends with Okta SSO, role-based access control, and audit trails.

• Multi-Agent Systems: Design agent coordination systems, skill discovery hubs, agent registries, and workflow orchestration.

• Enterprise Integration: Navigate Zscaler proxies, VPNs, SSL certificates, Kubernetes pod networking, DynamoDB, and AWS Bedrock.

• Testing and Quality: Write Playwright end-to-end tests before production deploy and maintain a 1000+ test suite with visual regression baselines.

• Deployment: Ship via GitLab CI/CD to AWS EKS (Kubernetes, ArgoCD, Helm, Secrets Manager) and diagnose pod restarts and liveness probe issues.

• Async and Performance: Debug event loop blocking, convert synchronous I/O to async, and optimize CPU-bound operations.

• Security: Partner with the CISO on PII/PHI de-identification, least privilege, and per-user OAuth2.

• Production Support: Debug authentication flows, token expiration, API rate limits, and health check failures.

You will ship 3-5 production tools in parallel within each sprint, deploying multiple times per day based on stakeholder feedback.
Servant Leadership and Mentorship (20%)
Guide 2-3 engineers through code reviews and pairing. Teach department leaders how to use AI tools effectively. Translate technical decisions for non-technical executives. No direct reports and no performance reviews. Pure servant leadership.

• Technical Mentorship: Code reviews, pairing sessions, and unblocking complex integrations.

• Non-Technical Teaching: Run discovery sessions with department VPs, teach Finance/HR/Legal leaders how to prompt AI tools, and build interfaces non-technical users can modify.

• Stakeholder Translation: Explain security trade-offs to executives and translate “OAuth2 delegation” into “everyone sees only their own data.”

• Remove Blockers: Clear obstacles for team members, escalate infrastructure issues, and coordinate across departments.

• Knowledge Sharing: Document patterns so others can self-serve and write playbooks department heads can follow without engineering help.

Daily Work

• Morning sync with the VP of AI Automation on build queue, blockers, and technical decisions.

• Direct coordination with 15+ stakeholders across departments.

• Discovery sessions with department leaders to map workflows.

• Hands-on coding: backend services, frontend components, and integration tests.

• Security reviews with the CISO.

• Ship multiple times per day and debug production issues.

• Code reviews for 2-3 team members.

Qualifications
Required

• 8+ years building production systems end-to-end (backend, frontend, integrations, infrastructure).

• Staff/Principal Engineer or Tech Lead experience, owning technical decisions on production systems.

• Shipped SaaS products with OAuth2, multi-tenancy, audit trails, and enterprise compliance.

• Deep AI/ML experience: production systems using LLM APIs (OpenAI, Anthropic, AWS Bedrock) and agent frameworks.

• Production Python: FastAPI, Pydantic, httpx, pytest (1000+ test suite experience).

• Production TypeScript/React: Next.js App Router, server components, Okta/NextAuth SSO, Playwright testing.

• AWS and Kubernetes: EKS operations, GitLab CI/CD, ArgoCD, Helm, Secrets Manager.

• Enterprise security patterns: Zscaler proxies, SSL certificates, Kubernetes networking, JWKS verification.

• Healthcare or regulated industry experience (HIPAA, SOC 2, or similar frameworks).

• Strong communication skills: run discovery sessions with non-technical stakeholders, explain security trade-offs to executives, and write architecture docs department leaders can follow.

• Servant leadership mindset: remove blockers for others, teach through questions not directives, and make stakeholders successful first.

• Thrives in organized chaos: 15 stakeholders, 6 systems, 3 sprints in flight.

• Bias toward shipping: “good enough to get feedback” beats “perfect in 3 months.”

• Highly collaborative: challenges ideas constructively and welcomes being challenged.

Preferred

• Led small teams (2-5 people) through technical mentorship or tech lead roles.

• US-based (US Central time zone preferred; Poland also considered).

• Built agentic systems: agent coordination, scheduled routines, and feedback loops.

• MCP (Model Context Protocol) experience: custom connectors for enterprise systems.

• Active contributor to AI/ML communities (papers, open source, conference talks).

• Teaching through code: strong code review skills, pairing experience, and documentation focus.

• Experience teaching non-technical users through workshops, training sessions, and business-user documentation.

AI-Augmented Engineering (Non-Negotiable)
DrFirst runs on AI-assisted development. We use Claude (Anthropic) as our primary AI model via AWS Bedrock for enterprise control, and we are standardizing on AI coding assistants for all development work.

• Active, daily use of AI engineering tools (Claude Code, GitHub Copilot, Cursor, Windsurf, Cline, or similar). Hard requirement. You should be writing code with AI assistants, not just using them occasionally.

• Experience with Claude (Anthropic) is highly valued, whether through Claude.ai, Claude Code CLI, API integration, or AWS Bedrock. Our automation platform runs on Claude Sonnet 4.5.

• At least one automation you have built that eliminated hours of manual work, ideally using LLM APIs.

• Comfort teaching others to use AI tools effectively through pairing and code review.

Technical Stack

• Backend: Python (FastAPI, Pydantic, httpx, pytest), OAuth2, AWS Secrets Manager, PostgreSQL, AWS Bedrock.

• Frontend: js 14 (React 18, TypeScript, Tailwind CSS), NextAuth.js/Okta SSO, Playwright.

• Infrastructure: AWS EKS (Kubernetes), GitLab CI/CD, ArgoCD, Helm, Zscaler proxies.

• AI and Agentic: Anthropic Claude (AWS Bedrock), AI coding assistants (GitHub Copilot/Cursor), MCP connectors.

Physical Requirements

• Primarily desk-based work, approximately 90-95% of the time, at a computer workstation.

• Occasional travel, less than 5-10% of the time.

Benefits
· Competitive compensation, with a base salary of $175,000 - $200,000 (Exact compensation may vary based on skills and experience)
· Eligible for Company Performance-based Bonus Program, based on individual and company performance
· Medical, dental, and vision insurance
· 401K eligible after 3 months of employment, with 50% company match up to first 5% of salary contributed to the plan with a 3-year vesting schedule
· HSA for eligible employees enrolled in the HDHP, with a generous company contribution up to $500 for individual coverage and $1000 for family coverage per year
· 100% company paid short and long-term disability, AD&D, and group life insurance
· Accrued annual paid time off (PTO) of 18 days for the first 3 years of service, increasing thereafter and 7 paid holiday days
· Employee Assistance Program
· Continuing Education funds up to $1500 annually for eligible programs after 1 year of service
· Voluntary benefits including FSA, Hospital indemnity, Accident and Critical Illness insurances
DrFirst is committed to being a Remote-First company, creating a dynamic and flexible workplace where everyone can thrive, no matter where they log in from. Check out our approach to remote work
Our recruitment process at DrFirst is straightforward and secure. You will only be contacted by our recruitment team through an official @drfirst.com email address. We will never ask you for payment or sensitive personal information, such as your social security number or banking details, at any stage of the hiring process. Additionally, we will not request that you purchase equipment or accept e-checks or checks for deposit. If you encounter any communications claiming to be from DrFirst that seem suspicious, please contact our recruitment team directly at to verify the message's authenticity. Your security is important to us!
Learn more about our benefits and professional development opportunities
Originally posted on Himalayas