About the role
Responsibilities:
- System Architecture: Research, design, and build highly reliable, distributed, available, and scalable platform services using Java.
- GenAI and LLM Integration: Build applied GenAI applications such as semantic search, automated beauty advisory bots, and multi-agent frameworks using open-source LLMs and APIs.
- RAG and Vector Data: Implement RAG workflows and manipulate vector databases (e. g., Pinecone, Milvus, PGVector) for high-performance context retrieval.
- Latency Optimisation: Optimise application architectures, databases, and LLM orchestration layers to minimise token-generation latency while keeping high throughput.
- Collaboration: Partner with core product managers, AI/ML research data scientists, and design teams to take features from a prompt-engineered prototype into robust enterprise production.
- Engineering Best Practices: Champion clean code, extensive Unit/Integration testing, CI/CD pipelines, and mentor junior developers in the team.
Requirements:
- Core Backend: Strong expertise in Java (8 or above), Spring Boot, Microservices, and RESTful APIs.
- Gen AI Stack: Proven experience with LLM frameworks like LangChain, LlamaIndex, or AutoGen, alongside basic proficiency in Python for running ML scripts or AI orchestration.
- Database Mastery: Solid hands-on knowledge of relational databases (MySQL/PostgreSQL) and NoSQL stores (Redis, MongoDB, or Cassandra).
- Foundational CS: Exceptional command over Data Structures, Algorithms (DSA), Object-Oriented Design Patterns, and concurrency.
- Cloud and Infrastructure: Hands-on experience with cloud deployment via AWS (EC2, S3, RDS) or similar platforms, using Docker / Kubernetes.
- AI Tooling (Good to have): Acquaintance with cloud AI frameworks like AWS Bedrock or OpenAI Enterprise APIs.