Marrina Decisions is seeking an AI Engineer to maintain and enhance the AI-driven backbone of the Sootra platform. The role involves ensuring production stability of LLM/VLM pipelines and optimizing model interactions while maintaining APIs and queues to improve AI outputs.
Responsibilities:
- Maintain and optimize LLM- and VLM-powered services for content generation, compliance scoring, and campaign testing
- Manage and scale Flask/FastAPI microservices, ensuring high uptime and low latency
- Maintain Dramatiq queues for async AI workflows, campaign generation, and pipeline orchestration
- Deploy, monitor, and debug Uvicorn/Gunicorn-based hosting in production environments
- Integrate with OpenRouter and equivalent LLM routing tools to balance cost, latency, and quality
- Design and refine prompt engineering strategies for reliability, context-awareness, and compliance
- Build and maintain feedback pipelines for AI model evaluation (human-in-the-loop scoring, automated quality checks, reinforcement)
- Expose and maintain REST APIs for AI services, ensuring secure, versioned endpoints
- Collaborate with backend/frontend teams to keep microservice architecture aligned and maintainable
- Track token consumption, latency, and error rates to ensure production-grade performance
Requirements:
- Minimum Experience: Mid-level
- Strong in Python, with experience in production-grade codebases
- Flask (for APIs), FastAPI (optional), Uvicorn/Gunicorn for async hosting
- Dramatiq (or Celery/RQ equivalent) for background jobs
- Hands-on with LLMs and VLMs, including prompt engineering, fine-tuning, and evaluation
- Familiar with OpenRouter or equivalent LLM/VLM routing & fallback tools
- Experience designing and maintaining microservice architectures
- Strong experience with REST API design (auth, rate limiting, documentation)
- Dockerized deployments, CI/CD pipelines, logging/monitoring, error handling
- Building structured evaluation/feedback systems for AI model performance
- AWS/GCP experience preferred (deployment, monitoring, scaling)
- 3–5 years as an AI Engineer or Python Backend Engineer working with production systems
- Prior work with SaaS platforms, LLM/VLM integrations, or AI-first products is highly valued
- Demonstrated ability to maintain AI pipelines in production, not just prototypes