J

Job Description:
Java Developer – AI Integration (Mid -Level)

Role Overview

We are looking for a
Mid -Level Java Developer (4 -9 years) with hands -on experience in AI integration
to join our product engineering team. In this role, you will be responsible for
embedding AI capabilities - including converting the user -provided natural
language inputs, or database metadata information into valid product
configurations, Retrieval -Augmented Generation (RAG), LLM -powered features, and
agentic workflows - directly into our Java/Spring Boot -based enterprise
product. You will work at the intersection of traditional backend engineering
and up-to-date AI/LLM technologies, owning the design, development, and maintenance
of AI -powered components end -to -end.

Key
Responsibilities:

AI Feature
Development

- Capture user intent via a conversational/chat
interface and translate it into valid product configurations.

- Extract metadata from heterogeneous sources -
file formats (CSV, Excel, PDF), relational database schemas, and API
contracts (OpenAPI, WSDL) and convert them to valid product
configurations.

- Design and implement RAG pipelines that retrieve
contextually relevant information from internal knowledge bases and
surface it through LLM -generated responses.

- Integrate LLM -powered features such as
intelligent chat, document summarization, content generation, and semantic
search into the existing product.

- Build and maintain AI agent workflows - including
tool use, multi -step reasoning chains, and orchestrated LLM calls - to
automate complex product -level tasks.

- Author, version, and iterate on system prompts
and user prompt templates to reliably steer LLM behavior.

- Apply advanced prompting techniques:
chain -of -thought, few -shot examples, output format enforcement, and
instruction following.





- Integrate with multiple LLM providers -
OpenAI/Azure OpenAI, Anthropic Claude, AWS Bedrock, and open -source models
(LLaMA, Mistral, etc.) - through their APIs.

- Build provider -agnostic abstraction layers using
Spring AI and LangChain4j to allow model switching without core code
changes.


Backend
Engineering

- Write clean, maintainable, production -grade Java
code following SOLID principles and enterprise design patterns.

- Integrate AI services with existing relational
databases via JPA/Hibernate, including schema design for storing
conversation history, embedding metadata, and audit trails.

- Manage build pipelines and dependency governance
using Maven or Gradle.

Testing &
Quality

- Write comprehensive unit, integration, and
contract tests for AI -integrated components.

- Handle non -deterministic LLM output gracefully -
implement fallback logic, retry strategies, and output validation.

- Monitor AI feature performance in production;
instrument logging and tracing for LLM calls, including token usage,
latency, and error rates.

Mandatory Skills
& Experience

Java & Backend

- 4–9 years of professional Java development
experience.

- Strong proficiency in Spring Boot - REST
controllers, service layer design, dependency injection, and configuration
management.

- Experience building and consuming RESTful
Microservices.

- Working knowledge of JPA/Hibernate -
entity modelling, JPQL,



transaction management.

AI / LLM
Engineering

- Hands -on experience integrating with at least one
major LLM provider API (OpenAI, Azure OpenAI, Anthropic, or AWS Bedrock)
from Java.

- Practical experience with Prompt Engineering - not just calling APIs, but crafting, testing, and iterating prompts to
achieve reliable, structured outputs.

- Experience building RAG pipelines -
document ingestion, chunking strategies, embedding generation, similarity
retrieval, and context injection into prompts.

- Working knowledge of LangChain4j and/or Spring
AI frameworks for LLM orchestration within Java applications.

- Understanding of AI agent concepts -
tool/function calling, agent loops, multi -step task orchestration.


Good -to -Have
Skills

- Experience with vector databases such as
Pinecone, Weaviate, Qdrant, pgvector, or Chroma for embedding storage and
semantic search.

- Exposure to multiple LLM providers (OpenAI, Anthropic Claude, AWS Bedrock, LLaMA/Mistral via Ollama or
similar).

- Familiarity with open -source LLM deployment - running models locally or on self -hosted infrastructure.

- Knowledge of token budgeting, context
window management, and cost optimization strategies for LLM APIs.

- Experience with observability tooling for
AI systems - LangSmith, Helicone, or custom logging pipelines.

- Familiarity with streaming responses from
LLMs (Server -Sent Events / WebSocket delivery to frontend).

- Understanding of embedding models - how
they differ from generative models, when to use which, and how to evaluate
embedding quality.

- Exposure to CI/CD pipelines and
containerization (Docker, Kubernetes).