Responsibilities
- Design and develop robust, scalable, and secure generative AI services and applications using Python and modern frameworks to drive enterprise-wide transformation
- Build and optimize high-performance, low-latency APIs and microservices for integrating advanced AI models and agentic workflows into our platform
- Collaborate closely with product managers, data scientists, and cross-functional engineering teams to translate complex business needs into innovative AI solutions, from concept to production
- Implement and maintain responsive user interfaces using technologies like React and TypeScript
- Partner with DevOps teams building continuous deployment, logging and monitoring; ensuring top-tier performance and reliability
- Own key architectural components, ensuring best practices in code quality, security, and maintainability through rigorous testing and peer reviews
Requirements
- 3+ years of hands-on experience as a software engineer, with strong Python development in production environments
- Proven expertise in building and deploying generative AI applications using LLMs, vector databases like Pinecone, Weaviate, pgvector, and modern open source agentic frameworks
- Deep knowledge and experience with microservices architecture, RESTful APIs, and cloud platforms such as AWS, GCP, or Azure, including Docker and Kubernetes containerization
- Solid understanding of FastAPI, Asyncio, and database systems like PostgreSQL
- Collaborative mindset with experience mentoring junior engineers
- Strong problem-solving skills with a proactive approach to system and process improvements
- Accountable for delivering high-quality, resilient, scalable code from conception to production
