Overview
Build AI-powered customer experiences for small businesses, designing and shipping production systems across the stack of Python, AI agents, React, Java/Spring Boot, LLMs, APIs and data layers.
What you'll do
- Design and build AI agents and LLM-powered features in Python, using tool/function calling, retrieval, and multi-step agentic workflows to solve real problems for small-business customers.
- Build AI features and workflows that integrate with the existing platform by utilizing Java/Spring Boot services, REST APIs, and data layers.
- Translate product requirements into clean, maintainable, well-tested code, including unit, integration, and API tests across frontend, backend, and AI components.
- Participate actively in code review and pull-request discussions, giving and receiving feedback.
- Debug and resolve production issues across frontend, Java services, Python, APIs, databases, and AI components using logs, tracing, browser tooling, and monitoring dashboards.
- Ship features that reach small-business customers directly, in an Agile/Scrum cadence with real sprint ownership.
- Contribute to a fast-moving, modernizing codebase, identifying opportunities to improve architecture, scalability, reliability, AI quality, and developer experience.
- Participate in technical design and architecture decisions, considering scalability, reliability, latency, cost, security, data flow, caching, asynchronous processing, and failure handling.
What you'll need
- 4+ years of professional software engineering experience, ideally building customer-facing production systems.
- Strong proficiency in Python, including building production services with FastAPI or similar frameworks.
- Hands-on experience building AI agents, including tool/function calling and multi-agent orchestration with frameworks such as LangGraph, OpenAI Agents SDK, Semantic Kernel, or CrewAI.
- Shipping Generative AI features to production, not just prototypes, with depth in at least one of RAG and vector search, prompt engineering, or LLM evaluation and observability.
- Ability to reason about AI and system-design tradeoffs across quality, latency, cost, scalability, reliability, and security.
- Proficiency in React, including hooks, component composition, state management, and building production-quality user experiences.
- Solid grasp of modern JavaScript/TypeScript, HTML5, and CSS3 fundamentals, with strong proficiency in Java and object-oriented programming.
- Strong understanding of REST APIs and backend services, with the ability to design, consume, debug, and trace issues end-to-end across frontend, Java services, databases, and AI integrations.
- Hands-on experience with Java and Spring Boot, including building production-grade REST APIs and backend services.
- Strong understanding of system design fundamentals, including API design, databases, caching, asynchronous processing, messaging/queues, scalability, reliability, observability, and distributed-system tradeoffs.
- AI-augmented delivery: use AI across the delivery lifecycle, not just code generation, and say which models suit which problems and where they are not used.
- Review AI-generated code knowing its failure modes, and work within clear boundaries for what customer data enters a prompt and what a security or compliance review will ask for.
Nice to have
- Experience with TypeScript, SQL, AWS/Azure/GCP, Kafka, Redis, vector databases, AI/ML frameworks, LLM evaluation/observability, or AI application frameworks such as LangChain/LangGraph.
Details
- Location: Mumbai, India.
- Work environment: work-from-home, hybrid, or work-from-the-office scenarios offered.
Read the full description and apply on the company’s own careers page.