About the Role

We are looking for a highly skilled Senior Backend Engineer to design, develop, and scale Al-powered applications and backend platforms. The ideal candidate will have strong expertise in backend engineering, cloud-native architectures, Retrieval-Augmented Generation (RAG) systems, Agentic Al frameworks, and production-grade LLM deployment. This role requires hands-on experience in building scalable Al solutions, optimizing cloud infrastructure, and ensuring reliability, observability, and security in production environments.

Responsibilities

1. Backend Engineering & Platform Development

- Design, develop, and maintain scalable backend services using Python, FastAPI, and asynchronous microservices architectures.
- Build and optimize data-intensive applications using PostgreSQL, Redis, MongoDB or equivalent technologies at production scale.
- Develop high-performance APIs and distributed systems to support AI-driven applications.

2. Cloud Infrastructure & DevOps

- Architect and manage cloud-native applications on AWS or GCP.
- Deploy and operate services using ECS, Lambda, Cloud Run, and other cloud-native technologies.
- Implement and manage Infrastructure as Code (IaC) using Terraform or equivalent frameworks like Pulumi, Cloudformation.
- Build and optimize CI/CD pipelines for reliable and automated deployments.

3. Retrieval-Augmented Generation (RAG) & Agentic AI Systems

- Design and implement production-grade RAG pipelines.
- Build hybrid retrieval systems using BM25, pgvector, vector databases, and semantic search techniques.
- Optimize retrieval accuracy, latency, and scalability for enterprise use cases.
- Build agentic workflows (LangGraph or similar) with tool calling, multi-step orchestration,



and production guardrails like fallback routing and human-in-the-loop controls.

4. Monitoring and Observability

- Instrument backend services end-to-end with metrics, distributed tracing, and structured logging using OpenTelemetry
- Hands-on with some observability stacks Prometheus + Grafana, Datadog/New Relic, and centralized logging (ELK/Loki)
- Build actionable dashboards and alerting to detect latency, errors, and resource bottlenecks before customer impact
- Experience with LLM/AI system observability token usage, latency, and quality tracing (Langfuse, LangSmith, Arize)

Requirements

- 4+ years of experience in backend development.
- B.E.B.TechB.S. Candidates' entries with significant prior experience in the fields above will be considered.
- Solid experience in Python development and FastAPI.
- Hands-on experience with asynchronous microservices architectures.
- Expertise in PostgreSQL, Mongodb, Redis, and distributed backend systems.
- Experience with AWS or GCP cloud platforms and Infrastructure as Code (Terraform, Cloudformation or equivalent).
- Strong understanding of CI/CD pipelines and DevOps best practices.
- Proven experience building and deploying RAG systems in production environments.
- Experience with LangGraph, tool calling, and agent-based AI architectures.
- Experience with development using AI coding agents like claude code, cursor, codex or equivalent.
- Guardrails in production: model fallback routing, prompt-injection defense, token cost budgets.
- Demonstrated ownership mindset with the ability to drive projects and deliver high-quality solutions.
- Experience in mentoring team members, conducting code reviews, and sharing best practices.

📌 Senior Backend Engineer (Python + Cloud) (Pune)
🏢 InFoCusp Innovations
📍 Pune