Senior Backend Engineer

Overview

Design, build, and scale production-grade asynchronous backend systems in Python for AI-native products, including multi-agent orchestration, retrieval-augmented generation, and provider-agnostic LLM integration. Take ideas from concept to production with ownership of architecture and outcomes.

What you'll do

• Design and scale async REST/WebSocket APIs in Python using dependency injection, type hints, and clean, vertical-slice architecture.
• Implement sequential, concurrent, and handoff multi-agent workflows to route work among specialized LLM agents.
• Integrate multiple LLM providers behind a provider-agnostic layer to enable A/B testing and cost-aware routing.
• Build and maintain Retrieval-Augmented Generation pipelines against vector stores such as pgvector, Chroma, or a managed vector search service.
• Design schemas and evolve data models using SQLAlchemy/SQLModel-style ORM plus migrations.
• Instrument services with structured logs, distributed tracing, and cost/latency metrics, maintaining p95 response-time standards under production load.
• Maintain end-to-end CI/CD ownership by linting, type-checking, testing, packaging, and deploying services.
• Champion AI across the delivery lifecycle and set guardrails for generated-code review, provenance and licensing checks, and customer data entering prompts.
• Move ideas from concept to production with ownership of architecture and outcomes.

What you'll need

• 5+ years building production backend systems in Python, with real async I/O experience.
• Hands-on experience designing and scaling REST or async APIs, including dependency injection and clean service architecture.
• Practical experience integrating LLM APIs, including OpenAI, Gemini, or similar, and building AI-readiness into backend systems from the ground up.
• Real experience with vector databases and RAG-style retrieval architectures.
• Strong relational database skills, including schema design, query optimization, and migration discipline.
• AI-augmented delivery experience across the delivery lifecycle, not just code generation.
• Ability to identify which models suit which problems and where not to use them.
• Experience reviewing AI-generated code and understanding its failure modes.
• Experience setting guardrails for generated-code review expectations, provenance and licensing checks, customer data entering prompts, and security or compliance reviews.
• End-to-end CI/CD ownership from build and test through packaging and deployment.
• A self-starting, go-getter mindset and comfort with ambiguity, fast iteration, and owning a problem until it is solved.

Nice to have

• Experience with multi-agent orchestration frameworks such as Semantic Kernel, LangChain, or similar.
• Experience with LLM cost and observability tooling.

Details

• Location: Mumbai, India.
• The company provides work-from-home, hybrid, or work-from-the-office environment scenarios.