Backend + AI

Recro; Bengaluru; On-site; INR 2,000,000 - 4,000,000; Full time

Job summary

Recro is seeking a Backend + AI Infrastructure Engineer in Bengaluru to build scalable backend services for AI applications and to integrate multiple LLMs into production systems.

You will design agentic AI workflows with LangGraph and LangChain, and implement asynchronous, event-driven architectures using Kafka and WebSockets. Strong focus on reliability, low latency, and high-concurrency support is required.

Qualifications

• Must have 3–5 years of backend engineering experience.
• Proficient in Python with FastAPI or Django.
• Experience with agentic AI systems (LangGraph, LangChain) is required.
• Experience with Redis caching.
• Strong background in building microservices.

Responsibilities

• Build scalable backend services for AI applications.
• Integrate LLMs (OpenAI, Claude, Gemini, Bedrock, or vLLM) into production.
• Develop agentic AI workflows using LangGraph, LangChain, or similar frameworks.
• Design asynchronous, event-driven systems (Kafka, RabbitMQ, WebSockets, SSE).
• Handle retries, rate limiting, circuit breakers, and provider fallback for AI services.

Skills

Backend engineering

Python (FastAPI/Django)

Agentic AI (LangGraph/LangChain)

Redis caching

Microservices

Tools

Kubernetes

Docker

Grafana

Prometheus

Kafka

RabbitMQ

WebSockets

Job description

This is not a Machine Learning or Data Science role.

It is a Backend + AI Infrastructure Engineer role responsible for:

• Building scalable backend services for AI applications.
• Integrating LLMs like OpenAI, Claude, Gemini, Bedrock, or vLLM into production.
• Building agentic AI workflows using LangGraph, LangChain, or similar frameworks.
• Designing asynchronous, event-driven systems using Kafka, RabbitMQ, WebSockets, or SSE.
• Handling retries, rate limiting, circuit breakers, and provider fallback when AI services fail.
• Optimizing AI performance using Redis caching and low-latency architectures.
• Building microservices that support high-concurrency production traffic (10,000+ concurrent users).
• Deploying and monitoring applications on AWS with Kubernetes, Docker, and observability tools like Grafana or Prometheus.

Mandatory Skill

• s3–5 years of backend engineering experience
• .Python (FastAPI/Django)
• .Agentic AI (LangGraph, LangChain, Multi-Agent Systems)
• .Redis caching
• .Microservices

.Good to Ha

• S.Observability (Grafana, Datadog, Prometheus
• .Fintech or payments experienc
• e.Startup experienc
• e.Experience breaking monoliths into microservice