Full-Stack Software Engineer, AI Applications
The Full-Stack Software Engineer at Confidential Client will build and maintain reliable, secure AI-enabled full-stack systems supporting clinical-trial and pharmaceutical workflows. The role involves developing backend Python services and frontend TypeScript features, debugging complex production issues, improving system reliability and observability, and integrating AI-driven functionalities within regulated environments. The engineer will take ownership of end-to-end software quality, from development through deployment and production verification, collaborating closely with AI experts and adhering to rigorous engineering standards.
About Careertakes
👉 Important disclosure: Careertakes is a third-party recruiting platform supporting this hiring process. If selected, you will be employed directly by our client, Technology — AI-enabled clinical-trial & pharmaceutical software.
Applicants for this role may also receive access to additional matched opportunities through the Careertakes platform.
About the role
Confidential Client is hiring a hands-on Full-Stack Software Engineer (AI Applications) to build and maintain production-grade, AI-enabled systems used in clinical-trial and pharmaceutical workflows. You will work across backend and frontend code, diagnose production issues, improve reliability and observability, and add safeguards around AI-driven features in regulated environments.
What You’ll Do
- Build and maintain full‑stack product features — Python services on the backend and TypeScript on the frontend.
- Implement and maintain backend APIs, database access, asynchronous jobs, queues, retries, and state transitions.
- Debug production problems with an evidence-driven approach: reproduce, narrow, hypothesize, instrument, fix, test, and verify.
- Trace changes across PRs, commits, CI runs, artifacts, deployments, logs, and user-visible behavior.
- Write behavior-focused tests and verify behavior at runtime in the environment where it actually runs.
- Improve system reliability, failure handling, backward compatibility, and observability.
- Add validation, structured outputs, fallbacks, and approval boundaries around AI-driven features in collaboration with the team’s AI experts.
- Communicate clearly about what is confirmed, assumed, incomplete, or still unverified.
What We’re Looking For
- Strong practical experience building and supporting production software systems.
- Strong Python experience: backend APIs, services, and database work.
- Strong TypeScript experience; broad fluency matters more than any single framework.
- Comfortable with asynchronous processing, retries, idempotency, state, and failure recovery.
- Sound engineering judgment around reliability, failure handling, backward compatibility, testing, and observability.
- Willingness to debug across system boundaries (not siloed to a single component).
- Fluency with Git, pull requests, code review, automated testing, CI/CD, and production verification.
- Effective and responsible use of AI coding agents while owning review, testing, and verification of their outputs.
- Evidence-based problem solving: reproduce, narrow, hypothesize, instrument, fix, test, and verify.
- Ability to learn unfamiliar frameworks and codebases quickly.
- A can-do attitude, ownership mentality, and clear communication.
Nice to have
- Experience with Django or another Python web framework.
- PostgreSQL or comparable relational-database experience.
- Familiarity with AWS, containers, Redis, queues, or async job systems.
- Experience with observability, tracing, and production debugging.
- Experience with agent frameworks (e.g., Pydantic AI) and production concerns: structured outputs, validation, fallbacks, model/provider switching, tracing, evaluation, cost/latency optimization, and safe handling of partial or failed tool execution.
- Experience in clinical, healthcare, pharmaceutical, or other regulated software (helpful but not required).
Success criteria (first few months)
- Independently investigate and resolve full‑stack and deployment-related problems.
- Deliver focused product improvements with meaningful tests and runtime verification.
- Prove which code and artifact are running in each environment.
- Improve reliability and observability for backend, asynchronous, and AI-driven workflows.
- Close the operational loop on work (verify deployments, environment behavior, and user impact).
How we work
- Responsible use of AI engineering tools — verify any AI-generated output yourself.
- Emphasis on production debugging, deployment verification, CI failures, environment consistency, and failure recovery as core engineering work.
- Clear, evidence-based communication about uncertainty and assumptions.
Details
- Seniority level: Entry level (production experience preferred)
- Employment type: Full-time
- Job function: Engineering and Information Technology
- Industry: Technology, Information and Internet; focused on AI-enabled clinical-trial & pharmaceutical software
- Location: Princeton, NJ, USA
Equal Opportunity & Hiring Transparency
Careertakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision-making. Final hiring decisions are made by people.
If you have questions about how your data is used, please contact us directly.
Negotiate a higher salary! Check the salary ranges for this job type in your area.
View My Salary Range