Develop, optimize, and maintain high-performance backend applications using Java (8/11/17).
Build robust microservices using Spring Boot / Spring Cloud.
Design scalable RESTful APIs and event-driven architectures.
Implement secure, highly available, low-latency backend systems.
Work with both relational and NoSQL databases such as MySQL, PostgreSQL, MongoDB, Redis.
Build and integrate AI agents using frameworks such as:
LangChain / LangGraph
OpenAI Assistants / ReAct / AutoGen
HuggingFace, LlamaIndex, or custom agentic frameworks
Develop advanced agentic workflows including:
Tool calling and function calling
Task planning and retrieval-augmented generation (RAG)
Dynamic reasoning and multi-agent collaboration
Integrate leading LLMs (GPT, Claude, Llama, Mistral, etc.) into Java-based systems.
Build workflows and pipelines for prompt engineering, model orchestration, and inference.
5–8 years of experience in Core Java, concurrency, multithreading, and performance tuning.
Strong expertise in Spring Boot, REST APIs, and microservices architecture.
Proficiency in SQL/NoSQL databases and integrating real-time data streams.
Solid understanding of LLMs, RAG, embeddings, and vector databases.
Practical experience building AI agent pipelines.
Hands-on experience with OpenAI API, LangChain, or similar frameworks.
Knowledge of prompt engineering and model fine-tuning techniques.
Demonstrated experience deploying AI-driven or agentic systems in production.
Familiarity with vector databases such as Pinecone, FAISS, Milvus, Weaviate.
Experience with cloud ecosystems (AWS, Azure, GCP) and containerization tools (Docker, Kubernetes).
Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related field.
Working knowledge of Python for interacting with core AI/ML services or models.
Experience with modern vector databases such as Weaviate, Pinecone, Chroma, etc.