About us
Arvya Tech is a service-first AI & SaaS startup delivering production-grade AI solutions for multiple clients across industries. Our work focuses on building scalable, secure, and high-performance AI-powered applications rather than research prototypes.
We are looking for a hands-on AI Engineer who can take ownership of end-to-end AI feature delivery, from design and implementation to deployment, monitoring, and optimization, while managing multiple projects in parallel.
What you'll own
- Design, build, and operate LLM-based features using Retrieval-Augmented Generation (RAG), vector databases, and embeddings.
- Develop and maintain AI-powered SaaS applications using Python.
- Deploy, manage, and monitor production-grade AI services on Microsoft Azure.
- Implement CI/CD pipelines for AI and backend services.
- Ensure high availability, low latency, and traffic handling for concurrent users.
- Monitor applications using logging, metrics, and alerts; troubleshoot production issues.
- Optimize performance and cost using caching, batching, async processing, and efficient architecture.
- Manage multiple client projects simultaneously with strong ownership.
- Collaborate with frontend, backend, DevOps, and product teams.
- Mentor junior engineers and contribute to technical reviews and delivery planning.
Must-have qualifications
- 23 years of professional experience building and deploying production software.
- Strong proficiency in Python (FastAPI/Flask, async programming).
- Hands-on experience with LLMs and RAG systems (embeddings, vector stores, retrieval, prompt engineering).
- Experience deploying and managing production applications.
- Solid Azure experience (Azure App Service, Azure ML, Azure OpenAI, AKS or similar).
- Experience with Docker and basic Kubernetes concepts.
- Familiarity with CI/CD pipelines, monitoring, and incident handling.
- Experience designing systems for scale, traffic management, and performance.
- Ability to multitask and manage multiple deliverables in a service-based environment.
- Strong communication skills and experience working with clients or cross-functional teams.
Nice-to-have
- Experience with LangChain, LlamaIndex, or similar LLM orchestration tools.
- Familiarity with vector databases (FAISS, Pinecone, Weaviate, etc.).
- Exposure to SaaS multi-tenant architectures.
- Experience with Redis, PostgreSQL, MongoDB.
- Basic knowledge of MLOps practices (model versioning, monitoring, retraining workflows).
What we offer
- Competitive compensation based on experience.
- Hybrid working model.
- Opportunity to work on real-world AI systems used by paying clients.
- Ownership of projects from design to production.
- Fast growth path toward Senior AI Engineer / Tech Lead roles.
- Startup environment with high impact and learning velocity.
How to apply
Send your resume and a brief note describing a production AI or SaaS project you worked on (architecture overview or repo link encouraged).
Email: [Confidential Information]
Subject line format:1114 AI Engineer
