Position: SDE-2 – AI Backend Engineer
Location: Noida (On-site – Sector 136)
Employment Type: Full-Time
Team: Artificial Intelligence, Automation & Platform Engineering
Experience: 2–5+ Years (strong system design & ownership can offset years)
About Aviara Labs
Aviara Labs is a next-generation AI automation and software engineering company based in Noida. We build AI-powered platforms, workflow automation systems, and intelligent enterprise solutions across domains like Healthcare, Legal Tech, Real Estate, Retail, and Customer Experience.
We operate at the intersection of Generative AI, distributed backend systems, and automation engineering, focusing on scalable, production-grade AI systems that solve real business problems.
Role Overview
We are looking for a strong Backend Engineer (SDE-2 level) with deep experience in Python, FastAPI/Django, and production backend systems, along with hands-on exposure to Generative AI (LLMs, RAG pipelines, AI agents, tool integrations).
This role is not just about API development — it requires end-to-end ownership of backend systems, including architecture, scalability, observability, performance tuning, and AI integration workflows.
You will work closely with AI engineers and product teams to build high-scale AI-native backend systems, integrating tools like OpenAI, Gemini, VAPI, 11Labs, Make, and n8n.
Key Responsibilities
Backend & System Design
- Design and build scalable, production-grade backend systems using Python (FastAPI / Django).
- Own end-to-end API architecture, service design, and database modeling.
- Design systems that handle high concurrency, async workloads, and long-running AI tasks.
- Implement caching, queues, background workers, and event-driven workflows.
GenAI & AI Integration
- Build and integrate LLM-powered features (RAG, agents, tool calling, embeddings pipelines).
- Work with OpenAI / Gemini / proprietary LLM APIs for real-world applications.
- Design prompt pipelines and AI orchestration layers for production use cases.
- Implement AI workflows using tools like n8n, Make, VAPI, 11Labs APIs.
Scalability & Production Engineering
- Deploy and manage services on AWS / Azure / GCP.
- Use Docker & Kubernetes for containerized deployments and scaling.
- Optimize system performance, latency, and cost efficiency.
- Implement logging, monitoring, metrics, and observability systems.
Code Quality & Engineering Ownership
- Write clean, testable, and maintainable production code.
- Participate in code reviews and enforce engineering best practices.
- Debug complex backend issues across services and integrations.
- Contribute to architectural decisions and system improvements.
Must-Have Skills
- Strong proficiency in Python, FastAPI, and/or Django.
- Solid understanding of system design and scalable backend architecture.
- Experience with PostgreSQL / MySQL / MongoDB.
- Hands-on with AWS / Azure / GCP in production environments.
- Experience with Docker and basic Kubernetes workflows.
- Understanding of GenAI concepts: RAG, embeddings, LLM APIs, agent workflows.
- Strong debugging and problem-solving skills in distributed systems.
- Experience working in fast-paced startup environments with an ownership mindset.
Good to Have
- Experience with message queues (Celery, Kafka, SQS, RabbitMQ).
- Vector databases (Pinecone, Weaviate, FAISS).
- Observability tools (Prometheus, Grafana, ELK stack).
- Prior experience building AI agents or automation workflows at scale.
- Experience leading modules or mentoring junior engineers.
