AI Engineer – SaaS Platform

This is a fully remote position, open to applicants in India.

📋 Description

• Oversee and enhance LLM- and VLM-powered solutions for content creation, compliance assessment, and campaign testing.

• Administer and scale Flask/FastAPI microservices, guaranteeing high availability and minimal latency.

• Manage Dramatiq queues to facilitate asynchronous AI workflows, campaign generation, and pipeline management.

• Deploy, monitor, and troubleshoot Uvicorn/Gunicorn-based hosting in live production settings.

• Integrate with OpenRouter and similar LLM routing tools to optimize cost, latency, and quality.

• Develop and improve prompt engineering strategies for consistency, context awareness, and compliance.

• Establish and uphold feedback systems for AI model assessment, including human-in-the-loop scoring, automated quality evaluations, and reinforcement learning.

• Provide and manage REST APIs for AI services, ensuring secure and versioned endpoints.

• Collaborate with backend and frontend teams to ensure the microservice architecture remains aligned and maintainable.

• Monitor token usage, latency, and error rates to ensure production-level performance.

⛳️ Requirements

• Proficient in Python with experience in production-level codebases.

• Experience using Flask for API development; familiarity with FastAPI is a plus.

• Experience with Uvicorn/Gunicorn for asynchronous hosting.

• Familiarity with Dramatiq, Celery, or RQ for managing background jobs.

• Practical experience with LLMs and VLMs, encompassing prompt engineering, fine-tuning, and evaluation.

• Knowledge of OpenRouter or similar LLM/VLM routing and fallback mechanisms.

• Experience in designing and managing microservice architectures.

• Strong background in REST API design, including aspects such as authentication, rate limiting, and documentation.

• Experience with Docker deployments, CI/CD pipelines, logging/monitoring, and error management.

• Experience in creating structured evaluation and feedback systems for AI model effectiveness.

• Preferred experience with AWS/GCP for deployment, monitoring, and scaling purposes.

• 3–5 years of experience as an AI Engineer or Python Backend Engineer engaged with production systems.

• Previous experience with SaaS platforms, LLM/VLM integrations, or AI-first products is highly regarded.

• Proven track record of maintaining AI pipelines in production rather than solely in prototype stages.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Flexible work hours and remote work opportunities.

• Comprehensive health, dental, and vision insurance.

• Generous paid time off and holiday policies.

• Continuous learning and professional development opportunities.