We are seeking an agile and highly skilled Senior Java Backend & Generative AI Engineer to join our rapidly evolving AI Platform team. This position is tailored for a strong backend engineer who has successfully transitioned into or heavily adapted their core skill set to build production-grade Generative AI pipelines and application logic.

You will own the development of secure, highly scalable microservices while orchestrating enterprise LLM connections. You will bridge the gap between robust, enterprise-grade Java backends and modern, intelligent AI workflows.

Key Responsibilities

- AI Backend Engineering: Design, develop, and implement scalable, fault-tolerant backend microservices and RESTful APIs using Java (11/17+) and the Spring Boot framework.

- GenAI Application Delivery: Lead the integration of Large Language Models (LLMs) into existing commercial software ecosystems, executing structural prompt engineering and tool-calling flows.

- RAG & Search Layer Optimization: Build and maintain high-efficiency Retrieval-Augmented Generation (RAG) systems, configuring semantic search indexing, embedding pipelines, and vector database retrieval.

- Cloud & Model Orchestration: Leverage AWS Bedrock and related cloud-native environments to consume, route, and optimize foundation models efficiently.

- Cross-Language Scripts:



Write and debug orchestration code or data-processing scripts natively in Python to support AI data loaders, data chunking frameworks, and model evaluation metrics.

- DevOps & Code Quality: Containerize software components using Docker, maintain structured Git branching strategies, and support automated CI/CD workflows for reliable deployment.

Technical Skills & Qualifications

Mandatory Core Skills

- Overall Experience: 4.5 to 6 years of dedicated commercial software engineering experience.

- Primary Backend Stack: Expert-level execution in Java Backend development, including deep hands-on mastery over Spring Boot, Spring Boot Data/JPA, and microservices design patterns.

- Generative AI Foundation: Proven technical experience building applications that interact with commercial or open-source LLM APIs (OpenAI, Anthropic, or Llama).

Valuable to Have (High Priority)

- Direct experience orchestrating foundational models natively via AWS Bedrock.

- Practical implementation of RAG architectures, including text-chunking techniques and vector database workflows (e.g., Pinecone, FAISS, PgVector, or OpenSearch).

- Mid-level coding proficiency in Python for configuring open-source AI frameworks (LangChain, LlamaIndex, or data processing stacks like Pandas/NumPy).

📌 Generative AI + Java (Pune)
🏢 TalentOla
📍 Pune