FULL STACK AI APPLICATION ENGINEER

Python / Java | Generative AI, RAG & Agentic AI

Experience: 3 to 7 years | Location: India / Remote / Offshore | Employment: Full-Time / Contract

About NForce One

NForce One is a technology services and solutions company with delivery capability across the United States and India. We build AI-powered products, enterprise applications, accelerators, and client-specific solutions across Generative AI, Agentic AI, Quality Engineering, Data Engineering, Cloud, and Digital Transformation.

Role Overview

We are looking for a hands-on Full Stack AI Application Engineer who is a strong software engineer first and an AI practitioner second. You will build complete, production-ready applications end to end, combining solid Python and Java engineering with modern front-end development and Generative AI, RAG, and Agentic AI capabilities.

You will own work across the full lifecycle: business requirements, solution design, backend development, database and vector store, LLM and agent integration, APIs, user interface, testing, cloud deployment, and production support. This is not a research, notebook-only, or model-experimentation role.

Key Responsibilities

· Design and develop AI-powered enterprise applications, assistants, copilots, intelligent search, and workflow automation solutions.

· Integrate commercial and open-source LLMs into production systems using prompt engineering, context engineering, structured outputs, tool and function calling.

· Build end-to-end RAG pipelines covering document ingestion, chunking, embeddings, vector storage, hybrid and semantic retrieval, metadata filtering, reranking, context construction, evaluation, and hallucination reduction.

· Build Agentic AI workflows including multi-agent systems, agent memory, planning, orchestration, supervisor agents, and human-in-the-loop flows.

· Develop backend services, REST APIs, and microservices in Python (FastAPI, Flask, Django) and Java (Spring Boot), with proper authentication, validation, error handling, logging, and versioning.





· Build responsive front-end interfaces with React or Angular and wire them to backend and AI services, including streaming LLM responses, chat interfaces, and authentication flows.

· Design and work with relational, NoSQL, and vector databases.

· Deploy, monitor, and support applications on Azure, AWS, or GCP using Docker, CI/CD pipelines, and standard observability tooling.

· Build reusable AI services and components, and evaluate emerging AI frameworks and models for adoption.

· Contribute to AI-powered automation and quality engineering initiatives such as test generation, defect triage, root cause analysis, and self-healing automation.

· Translate business requirements into technical solutions, build rapid POCs, and convert successful POCs into production applications.

Required Qualifications

· 3+ years of professional software development experience.

· Strong hands-on Python development, writing maintainable production code (not limited to notebooks).

· Hands-on Java and Spring Boot development experience.

· Proven experience designing and building REST APIs and backend services.

· Full stack application development experience, including hands-on front-end work with JavaScript or TypeScript and React or Angular, plus HTML and CSS.

· Strong SQL and relational database experience (PostgreSQL, MySQL, SQL Server, or Oracle).

· Hands-on Generative AI / LLM integration experience in real applications.

· Experience building or contributing to RAG-based applications.

· Hands-on experience with at least one major cloud platform (Azure, AWS, or GCP).

· Proficiency with Git and strong software engineering fundamentals.

Preferred Qualifications





· 4 to 7 years of overall IT experience, including 2+ years each in Python and Java application development.

· Hands-on experience with LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, or Semantic Kernel.

· Experience building and deploying AI agents in production.

· Vector database experience: Pinecone, Weaviate, ChromaDB, FAISS, pgvector, Azure AI Search, or OpenSearch.

· Microservices architecture, Docker, Kubernetes, and CI/CD (Jenkins or GitHub Actions).

· Practical ML understanding (classification, regression, clustering, feature engineering, model evaluation and deployment) with Scikit-learn, XGBoost, or Hugging Face.

· Test automation exposure: Playwright, Selenium, RestAssured, PyTest, TestNG, JUnit, or Postman.

· Data engineering exposure: PySpark, Kafka, Airflow, Azure Data Factory, AWS Glue, ETL/ELT pipelines.

· Databricks experience: Delta Lake, Medallion Architecture, Unity Catalog, Workflows, Databricks SQL.

· Monitoring and observability tools: Grafana, Prometheus, Datadog, Azure Monitor, CloudWatch.

Nice to Have

GraphRAG, fine-tuning and LoRA/PEFT, TensorFlow, PyTorch, MLflow, Terraform, JMeter or performance testing, Appium, Next.js, state management libraries, component design systems, and multi-cloud experience.

Ideal Candidate Profile

You are a hands-on coder who is comfortable in both Python and Java, capable of building the user interface as well as the services behind it, curious about emerging AI technologies, and able to independently ship a feature from design through to production. You troubleshoot on your own, learn recent frameworks quickly, and collaborate easily with product owners, architects, QA engineers, UI developers, and client teams.

Education

Bachelor's or Master's degree in Computer Science, Information Technology, Artificial Intelligence, Data Science, or Engineering, or equivalent hands-on software development experience.

NForce One is an equal opportunity employer. We welcome applicants from all backgrounds.

📌 Full Stack AI Application Engineer (Hyderabad)
🏢 NForce One
📍 Hyderabad