Back End Developer

Job Description

Title: Backend Developer

Location: Jaipur, Noida, Gurgaon, Pune, Bengaluru, Hyderabad

Duration: Fulltime

Experience: 3–5 years

Role Overview

We are looking for a skilled Backend Developer to build, scale, and optimize high-performance backend systems supporting AI-driven applications, data platforms, and agentic workflows. The role involves designing APIs, integrating LLM-based systems, handling large-scale data pipelines, and ensuring secure, reliable, and scalable backend services.

Key Responsibilities

• Design, develop, and maintain scalable backend services using Python, with strong handling of synchronous and asynchronous execution models.

• Build and deploy backend systems that support LLM-based applications, including prompt-driven workflows, RAG pipelines, and fine-tuned models.

• Develop API-first architectures using FastAPI, including middleware design, authentication mechanisms, ORM-based database interactions, migrations using Alembic, and proxy/networking configurations.

• Work with agentic frameworks such as LangChain and LangGraph to orchestrate complex AI workflows, and use LangSmith / LangFuse for observability, tracing, and evaluation.

• Build and maintain data pipelines leveraging Databricks, including Delta Lake and core Databricks services for reliable data storage and processing.

• Integrate message queue and streaming systems such as Redis for event-driven and asynchronous communication.

• Develop backend services that interact with cloud infrastructure, primarily using AWS core services for compute, storage, networking, and deployment.

• Collaborate closely with data scientists, ML engineers, and platform teams to productionize AI solutions with strong focus on performance, security, and scalability.

Required Skills & Qualifications

• Strong backend development experience in Python, including async frameworks and concurrency handling.

• Hands-on experience with FastAPI and modern backend architecture patterns.

• Solid understanding of LLMs, prompt engineering, RAG, and fine-tuning workflows.

• Experience with agent-based systems and LLM orchestration frameworks.

• Working knowledge of Databricks and Delta Lake for data engineering use cases.

• Experience with event-driven architectures using Kafka or NATS.

• Familiarity with AWS services and cloud-native backend deployments.

• Understanding of containerization and orchestration concepts (basic level acceptable).

Good to Have

• Exposure to LLMOps / Model observability practices.

• Experience deploying AI-backed APIs in production environments.

• Understanding of backend security, authentication flows, and network-level considerations.