Senior Full Stack Engineer

Invictus AI is an AI-first, AI-native company. This role is central to building AI-powered products and autonomous agents that reason, retrieve information, and take action across enterprise systems. We are seeking a senior engineer who not only builds high-quality systems, but also designs and operates production-grade AI agents that deliver measurable business impact.

• 7+ years of full-stack software engineering experience
• Proven ownership from architecture through production in complex systems
• Expert‑level Python and Django/Django REST Framework
• Deep Postgre
  
  SQL expertise (query optimization, indexing, migrations)
• Asynchronous processing (Celery or similar) and Redis
• Strong authentication and authorization (OAuth 2.0, JWT)
• Experience designing AI‑enabled backend systems in production

• Hands‑on experience building production AI agents (multi‑step, tool‑using systems)
• Strong understanding of:
• RAG architectures and retrieval trade‑offs
• Tool and function calling patterns
• Agent memory (short‑term and persistent)
• Planning and reasoning workflows
• Experience integrating LLMs with external APIs (Google, Microsoft, CRM, document systems)
• Designing guardrails, evaluation frameworks, and observability for non‑deterministic systems
• Managing latency, cost, batching, and caching strategies for AI workloads
• Familiarity with vector databases and embeddings
• Experience selecting models and providers based on performance and cost constraints

• Strong React Native and Type Script experience
• Experience building AI‑assisted user interfaces (chat, copilots, workflow automation)
• Production deployment to iOS and Android
• Understanding of state management and performance optimization

• Production experience with AWS and GCP
• AWS services such as ECS, RDS, S3, Elasti Cache
• GCP services such as GKE, Cloud SQL, Cloud Storage, Vertex AI
• Docker containerization and CI/CD implementation
• Infrastructure as Code (Terraform or similar)

• Design and build AI agents that can reason, retrieve information, and take actions across enterprise systems
• Implement reliable, secure, and cost‑efficient LLM integrations
• Architect scalable APIs, background job systems, and real‑time services
• Establish best practices for AI evaluation, monitoring, and guardrails
• Optimize performance, reliability, and cost across AI and application layers
• Mentor engineers and elevate AI‑native development standards

We are seeking an engineer with strong system design judgment, production rigor, and the ability to build autonomous AI systems that operate reliably in real‑world environments.