Senior Backend Engineer (Python) — GenAI/Agentic Systems Exposure

About the Role

We're looking for a Senior Backend Engineer to design and build scalable, cloud-native backend systems using Django and FastAPI. This is primarily a backend architecture and leadership role — you'll own service design, database performance, and API reliability — with a meaningful slice of the work involving LLM-powered features: RAG pipelines, tool-calling agents, and integrations with vector databases. You'll drive technical decisions, mentor engineers, and be a hands-on senior IC who can also lead design discussions.

Role mix: ~75% core backend engineering, ~25% GenAI/agentic feature work.

Responsibilities

Backend Architecture & Engineering (core)

Design and architect scalable, high-performance backend services using Django and FastAPI

Lead technical design discussions and conduct architecture reviews for new features and systems

Create, maintain, and document RESTful APIs with a focus on reliability, security, and versioning

Design efficient database schemas, optimize complex queries, and ensure data integrity (PostgreSQL/MySQL)

Design and implement cloud-native solutions leveraging microservices and serverless architectures

Conduct thorough code reviews and enforce coding standards across the team

Provide effort estimations for project and sprint planning

Guide and mentor junior and mid-level engineers on best practices and technical growth

Collaborate with product, QA, and DevOps to drive projects to completion

Document technical specifications, architecture decisions, and API contracts

GenAI / Agentic Systems (applied)

Design and integrate LLM-powered features into existing backend services — RAG pipelines, tool-calling agents, and structured-output workflows

Build retrieval pipelines using embeddings, vector databases, and document chunking strategies

Integrate LLM agents with internal systems and third-party APIs, with attention to reliability (retries, timeouts, validation, guardrails)

Make pragmatic build-vs-integrate calls on LLM providers and orchestration frameworks based on cost, latency, and maintainability

Requirements

5–7 years of backend development experience with strong proficiency in Django and FastAPI

Deep understanding of SQL, query optimization, and Django ORM / SQLAlchemy

Hands-on experience with Docker containerization

Solid understanding of microservices and event-driven architectures

Experience building and deploying serverless backends (AWS Lambda, Azure Functions)

Proficiency in cloud platforms (AWS/Azure) including deployment, monitoring, and debugging

Practical experience integrating LLM APIs (OpenAI, Anthropic, or similar) into production applications

Working knowledge of RAG architecture and at least one vector database (pgvector, Pinecone, Qdrant, Weaviate, or similar)

Proven experience in effort estimation, technical planning, and architecture reviews

Strong communication skills and experience mentoring junior developers

Good to Have

Experience with an agent framework or SDK — LangChain, LangGraph, or Claude Agent SDK (framework-agnostic; any one of these is a plus)

Familiarity with MCP (Model Context Protocol) for tool/agent integration

Experience with message queues (RabbitMQ, Kafka, SQS)

Familiarity with CI/CD pipelines and DevOps practices

Exposure to performance profiling and optimization techniques

Experience fine-tuning or working with open-weight models (LoRA/QLoRA) — not required, nice signal of depth