About the role
Responsibilities:
- Design and build highly scalable, secure, and resilient backend systems using Java and/or Node.js .
- Architect microservices and distributed systems capable of handling high-traffic and low-latency workloads.
- Build and integrate AI/LLM-powered features into backend applications.
- Develop RAG-based applications, AI agents, and intelligent automation workflows.
- Integrate OpenAI, Anthropic, Gemini, or other LLM APIs into enterprise products.
- Work with vector databases and embedding pipelines to build semantic search and knowledge retrieval systems.
- Collaborate with Product, AI/ML, and Engineering teams to translate business requirements into scalable technical solutions.
- Drive engineering best practices, code quality, performance optimisation, and security.
- Mentor engineers through design reviews, code reviews, and technical guidance.
- Lead architecture discussions and contribute to long-term technical strategy.
Requirements:
- 8-12 years of backend development experience.
- Strong hands-on experience with Java (Spring Boot) and/or Node.js .
- Expertise in designing REST APIs, Microservices, and Event-Driven Architecture.
- Strong understanding of Distributed Systems, System Design, Concurrency, and Scalability.
- Experience with cloud platforms such as AWS, Azure, or GCP.
- Hands-on experience with Docker, Kubernetes, and CI/CD pipelines.
- Experience with SQL and NoSQL databases (PostgreSQL, MySQL, MongoDB, Redis, etc. ).
- Strong understanding of Kafka/RabbitMQ or other messaging systems.
AI/GenAI Experience (Mandatory):
- Hands-on experience building AI-enabled products or integrating AI into production applications.
- Experience working with LLMs such as OpenAI GPT, Claude, Gemini, Llama, or similar models.
- Strong understanding of RAG (Retrieval-Augmented Generation) architecture.
- Experience with LangChain, LangGraph, LlamaIndex, or similar AI orchestration frameworks.
- Experience with Vector Databases such as Pinecone, PGVector, Milvus, ChromaDB, Weaviate, or Qdrant.
- Experience in Prompt Engineering, Embeddings, Semantic Search, AI Agents, and AI workflow orchestration.
- Knowledge of AI evaluation, guardrails, and prompt optimisation is a plus.
Good to Have:
- Experience with Agentic AI frameworks such as CrewAI, AutoGen, ADK, or similar.
- Experience in FinTech, SaaS, or large-scale product companies.
- Exposure to ML pipelines and MLOps.
- Experience leading engineering teams or mentoring senior developers.