AI-Native Full-Stack Software Engineer / Technical Project Manager
Zenara Health
IndiaremotePosted 21 days ago
Z
Skill Required
EngineeringMental-HealthcareFullstack-DevelopmentAI-EngineeringTechnical-Project-ManagementAI-Native-Fullstack-EngineerAI-Native-Software-EngineerAI-Full-Stack-EngineerSenior-Full-Stack-AI-EngineerAI-Native-Product-EngineerSenior-Full-Stack-AI-DeveloperFull-Stack-AI-EngineerAI-Full-Stack-DeveloperFull-Stack-AI-DeveloperSoftware-EngineerTechnical-Project-ManagerDeveloperFull Stack DeveloperAI EngineerEngineering ManagerTechnical LeadSoftware EngineerSoftware DeveloperAIObservabilityCybersecurityCD pipelinesWeb AccessibilitydesigningdebuggingsecuritybuildingTestNGdesignCI/CDCloudAPIsGenerative AIandCICDFulltime
Key highlights
- Competitive, based on demonstrated ability and experience
- Approximately 5–8 years of professional software engineering experience, or equivalent demonstrated ability
- Fully remote work with flexible paid time off
- 50 hours per week with required meeting overlap 6:00 PM–12:00 AM IST
- Experience owning delivery end-to-end (not only own tasks) is a must-have
- Direct and regular access to the founders, without intermediaries
Role overview
Zenara Health is a technology-oriented mental healthcare organization focused on enhancing accessibility and quality of mental wellness services. They integrate AI-driven platforms with professional clinical care to offer personalized and effective mental health solutions. They are building an AI-native software factory: an engineering system where coordinated swarms of specialized agents can translate product requirements into architecture, implementation, tests, security checks, documentation, deployments, and continuous improvements — with engineers providing direction, judgment, and governance. This is a hands-on, mid-level role in a fast-moving startup where the engineer will help design and operate this software factory, including agent roles, orchestration, context architecture, tool access, testing, security, evaluations, and human review workflows.
Responsibilities
- Design, build, test, deploy, and maintain full-stack product features.
- Develop AI-native applications and workflows using autonomous agents, LLMs, tools, APIs, retrieval systems, and structured data.
- Build agentic systems that can plan and execute multi-step tasks with appropriate observability, evaluation, permissions, and human oversight.
- Use autonomous development agents to accelerate implementation, testing, debugging, refactoring, documentation, and code review without compromising engineering quality.
- Build and operate multi-agent workflows across product discovery, architecture, development, testing, security, deployment, and maintenance.
- Define clear agent responsibilities, communication patterns, permissions, escalation paths, and quality gates.
- Design robust backend services, APIs, data models, integrations, and modern frontend experiences.
- Contribute to system architecture and make practical decisions involving scalability, reliability, security, cost, and maintainability.
- Create evaluation frameworks and feedback loops for measuring agent quality, accuracy, reliability, and business impact.
- Develop safeguards that prevent agents from introducing architectural drift, security vulnerabilities, unreliable code, or unnecessary complexity.
- Implement protections against AI-specific risks, including hallucinations, prompt injection, excessive permissions, data leakage, and unreliable tool execution.
- Measure the software factory's effectiveness using delivery speed, defect rates, test coverage, reliability, cost, and business outcomes.
- Work with cloud infrastructure, CI/CD pipelines, containers, logs, monitoring, secrets, environments, and production deployments.
- Apply foundational cybersecurity practices across application development and infrastructure.
- Collaborate directly with founders, product stakeholders, customers, and other engineers.
- Take ownership from initial problem definition through production deployment and ongoing improvement.
- Continuously evaluate emerging agentic AI frameworks, models, protocols, and development practices.
- Gradually take ownership of coordinating the agent swarm and shaping the next generation of our AI-native engineering organization.
Requirements
- Approximately 5–8 years of professional software engineering experience, or equivalent demonstrated ability.
- Experience owning delivery end to end, not only your own tasks. You have seen how a whole product goes together, you can plan and sequence the work, and you have carried something over the finish line.
- Strong full-stack development skills across modern frontend frameworks such as React, Next.js, or equivalent.
- Backend development using Python, TypeScript, Node.js, or similar technologies.
- Experience with REST, GraphQL, event-driven, or asynchronous system integrations.
- Relational and/or NoSQL databases experience.
- Strong understanding of software architecture, API design, data modeling, testing, and production engineering.
- Practical experience building with LLMs or agentic AI systems — not only using AI coding assistants.
- Understanding of agentic AI concepts such as tool use and function calling, planning and multi-step execution, agent orchestration and delegation, multi-agent collaboration, memory and context management, retrieval-augmented generation, structured outputs and validation, model selection and routing, evaluations tracing and observability, guardrails and permission boundaries, and human-in-the-loop workflows.
- Ability to assess AI-generated code critically and validate it through tests, reviews, security checks, and architectural reasoning.
- Working knowledge of cloud infrastructure, containers, CI/CD, production monitoring, and deployment practices.
- Basic understanding of cybersecurity principles, including authentication and authorization, encryption and secrets management, secure API design, dependency and supply-chain security, data privacy and access controls, and common web application vulnerabilities.
- High ownership, curiosity, and comfort working in an ambiguous startup environment.
- A strong desire to remain at the cutting edge of agentic AI and AI-native software development.
- Clear written and verbal communication skills.
- Availability for the required meeting overlap with US Pacific Time, and a commitment of approximately 50 hours per week.
Nice to have
- Experience in healthcare, health technology, clinical workflows, or regulated software environments.
- Familiarity with healthcare data standards and requirements such as HIPAA, FHIR, HL7, PHI handling, auditability, or role-based access control.
- Experience with agent frameworks, orchestration systems, MCP, vector databases, or LLM observability and evaluation platforms.
- Experience building multi-agent systems or long-running autonomous workflows.
- Experience designing AI-based development workflows or internal engineering automation.
- Familiarity with infrastructure as code, Kubernetes, serverless systems, or major cloud platforms.
- Experience with security reviews, threat modeling, compliance, or privacy-sensitive applications.
- Previous experience working in an early-stage startup.
Benefits
- Competitive compensation, based on demonstrated ability and experience
- Fully remote work
- Equipment allowance
- Local public holidays
- Flexible paid time off
- Direct and regular access to the founders, without intermediaries
Additional details
- Location: Remote
- Type: Full-time
- Working Hours: All meetings and live collaboration happen between approximately 6:00 PM and 12:00 AM IST, overlapping US Pacific Time. Attendance in that window is required. Your remaining work is yours to schedule.
- Commitment: Approximately 50 hours per week
- Industry: Healthcare technology experience is preferred but not mandatory
- The role is not a project management role only — it requires both technical depth and project ownership.
- The difference in this role is who the team is: coordinating agents rather than twenty engineers.
- The goal is not to eliminate engineering accountability but to enable a small, highly capable engineering team to deliver software with dramatically greater speed, quality, and consistency.
- As you grow in this role, you will have the opportunity to lead this software factory and direct a swarm of autonomous development agents.
- Schedule details: Meetings and live collaboration take place between approximately 6:00 PM and 12:00 AM IST, overlapping US Pacific working hours. Attendance in that window is required. Outside that window, you decide when you work. We care about output, reliability, and being reachable when the team needs you — not clock-in times. The role carries a commitment of approximately 50 hours per week, and availability is expected during critical deployments and incidents.
- Experience with any specific model or framework is useful, but we value your ability to understand and apply the underlying principles more than expertise in one particular tool.