REMOTE (INDIA): AI Engineer- SaaS Platform

Marrina Decisions

20h•Remote

About The Position

We are looking for an AI Engineer to maintain and enhance the AI-driven backbone of the Sootra platform. The role focuses on keeping LLM- and VLM-powered pipelines stable in production, optimizing model interactions, maintaining APIs and queues, and developing feedback loops that continually improve AI outputs. The engineer will work with backend and frontend teams to keep the platform’s microservice architecture aligned and maintainable.

Requirements

Strong Python skills and experience working in production-grade codebases.
Experience with Flask; FastAPI is optional.
Experience with Uvicorn/Gunicorn for asynchronous hosting.
Experience with Dramatiq or an equivalent background-job tool such as Celery or RQ.
Hands-on experience with LLMs and VLMs, including prompt engineering, fine-tuning, and evaluation.
Familiarity with OpenRouter or equivalent LLM/VLM routing and fallback tools.
Experience designing and maintaining microservice architectures.
Strong REST API design experience, including authentication, rate limiting, and documentation.
Experience with Dockerized deployments, CI/CD pipelines, logging, monitoring, and error handling.
Experience building structured evaluation and feedback systems for AI model performance.
3–5 years of experience as an AI Engineer or Python Backend Engineer working with production systems.
Demonstrated ability to maintain AI pipelines in production, not just prototypes.

Nice To Haves

AWS or GCP experience, including deployment, monitoring, and scaling.
Prior work with SaaS platforms, LLM/VLM integrations, or AI-first products is highly valued.

Responsibilities

Maintain and optimize LLM- and VLM-powered services for content generation, compliance scoring, and campaign testing.
Manage and scale Flask/FastAPI microservices to support high uptime and low latency.
Maintain Dramatiq queues for asynchronous AI workflows, campaign generation, and pipeline orchestration.
Deploy, monitor, and debug Uvicorn/Gunicorn-based hosting in production environments.
Integrate OpenRouter or 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 AI model evaluation feedback pipelines, including human-in-the-loop scoring, automated quality checks, and reinforcement.
Expose and maintain secure, versioned REST APIs for AI services.
Collaborate with backend and frontend teams to keep the microservice architecture aligned and maintainable.
Track token consumption, latency, and error rates to maintain production-grade performance.