AI Engineer- SaaS Platform in India at Jobgether

This position is posted by Jobgether on behalf of a partner company. We are currently looking for an AI Engineer – SaaS Platform in India.

This role is focused on maintaining and scaling the AI backbone of a production-grade SaaS platform powered by LLMs and VLMs. You will be responsible for ensuring the stability, performance, and continuous improvement of AI-driven services used for content generation, compliance scoring, and automated campaign workflows. The position requires strong backend engineering expertise combined with practical experience in deploying and operating AI systems in real-world production environments. You will work on optimizing microservices, managing asynchronous processing pipelines, and improving API reliability and scalability. A key aspect of this role is building feedback loops that enhance model outputs over time through structured evaluation and human-in-the-loop systems. This is a highly technical, hands-on role in a fast-moving AI-first environment where engineering excellence directly impacts product intelligence and user outcomes.

• Maintain and optimize LLM- and VLM-powered services for content generation, compliance scoring, and campaign testing workflows.
• Manage and scale Flask and FastAPI microservices, ensuring high availability, low latency, and system reliability.
• Design, maintain, and monitor Dramatiq (or equivalent) queues for asynchronous AI workflows and pipeline orchestration.
• Deploy and support Uvicorn/Gunicorn-based services in production, ensuring stability and efficient resource utilization.
• Integrate and manage OpenRouter or similar LLM routing tools to optimize cost, latency, and model quality trade-offs.
• Design prompt engineering strategies to improve accuracy, contextual awareness, and compliance of AI outputs.
• Build and maintain AI feedback loops, including human-in-the-loop evaluation and automated quality assessment systems.
• Develop and maintain secure, versioned REST APIs for AI services with proper authentication and rate limiting.
• Collaborate with backend and frontend teams to ensure a scalable and maintainable microservices architecture.
• Monitor production metrics such as token usage, latency, and error rates to ensure optimal system performance.

• 3–5 years of experience as an AI Engineer or Python Backend Engineer working with production systems.
• Strong proficiency in Python with experience in production-grade backend development.
• Hands-on experience with Flask and familiarity with FastAPI, Uvicorn, and Gunicorn.
• Experience working with background job systems such as Dramatiq, Celery, or RQ.
• Practical experience with LLMs and VLMs, including prompt engineering, evaluation, and fine-tuning concepts.
• Experience integrating or working with LLM routing platforms such as OpenRouter or equivalent tools.
• Strong understanding of microservices architecture and scalable system design.
• Solid experience designing and maintaining REST APIs, including authentication and rate limiting.
• Familiarity with Docker, CI/CD pipelines, logging, monitoring, and production debugging.
• Experience building AI evaluation or feedback systems is highly desirable.
• Exposure to cloud platforms such as AWS or GCP for deployment and scaling.
• Prior experience with SaaS or AI-first product environments is a strong advantage.

• Competitive compensation aligned with experience and industry standards.
• Opportunity to work on cutting-edge LLM/VLM-powered SaaS products.
• Fully remote or flexible work environment within India (as applicable).
• Exposure to modern AI infrastructure, microservices, and production-scale systems.
• Strong focus on engineering excellence, automation, and system scalability.
• Career growth opportunities in AI engineering and platform architecture.
• Collaborative, product-driven environment with high technical ownership.