Sign in to see your fit: the skills, experience and location this job asks for, checked against your profile.
Job description
Location: Ahmedabad, India Compensation: INR 45000000 - 50000000 per year
Role Overview: Principal Software Engineer (AI) will lead the design, development, and delivery of production-grade AI and LLM-powered applications. This role combines hands-on engineering with technical leadership—building scalable AI services, RAG pipelines, and agentic workflows while mentoring engineers and partnering with product, data, and design teams.
Key focus areas
AI and LLM engineering
LLM integration: Build applications on large language models such as Azure OpenAI, OpenAI, Anthropic or open-source models. This includes prompt design, function and tool calling, and structured outputs.
RAG (retrieval-augmented generation): Design retrieval pipelines that cover document ingestion, chunking, embeddings, vector search, re-ranking and grounding responses in trusted sources.
AI agents and orchestration: Build agentic workflows using Claude/Co-pilot/Gemini.
Evaluation and guardrails: Set up evaluation frameworks that measure accuracy, hallucination rate, latency and cost. Add safety filters, PII handling and content moderation.
Python and backend development
Python: Strong skill in Python/Java/Php for AI development, including async programming, type hints and packaging.
API development: Build RESTful APIs (FastAPI, Flask or ASP.NET Core) that expose AI features, with streaming responses, serialization and versioning.
Application architecture: Understanding of dependency injection, middleware, configuration and clean, maintainable project structure.
Data and storage
SQL: Strong skill in SQL, including joins, query optimization and working with Microsoft SQL Server.
Vector databases: Hands-on experience with Azure AI Search, Pinecone or similar.
Data pipelines: Prepare, clean and transform structured and unstructured data (PDFs, documents, logs) for AI workloads.
Communication
Strong communication skills, including the ability to explain AI capabilities, limitations and trade-offs to technical and non-technical stakeholders.
Also required
ML fundamentals: Understanding of embeddings, tokenization, fine-tuning, model selection and the basics of how transformers work.
Cloud and MLOps: Design and deploy AI solutions on Azure (preferred), AWS or GCP. Experience with Azure AI Foundry or Azure ML, containerization (Docker, Kubernetes), CI/CD for AI services, and model and prompt versioning.
Performance and scalability: Optimize AI systems for latency, throughput and token cost through caching, batching, concurrency and rate-limit handling.
Queue management: Design message queues for reliable, asynchronous AI processing pipelines and communication between services.
Collaboration: Work closely Product Owners, data teams, designers and front-end developers to turn business problems into AI solutions.
Code review and mentoring: Review code, give constructive feedback, and mentor junior engineers on AI engineering best practices.
Must have
8+ years of software development experience, with 2+ years in AI/ML or LLM-based applications
Strong skill in Python/Java/Php
Hands-on experience with LLM APIs, prompt engineering and RAG architectures
Experience with Azure cloud services, especially Azure OpenAI and Azure AI Search or similar
Proficiency in Microsoft SQL Server and at least one vector database
Experience shipping AI features to production, not just prototypes
Excellent verbal and written communication skills, with the ability to explain complex ideas clearly
Skills: Java,Python, LLMs, RAG, Prompt Engineering, Vector Databases, SQL Server, Communication and Articulation
Good to have
Experience with Angular or React for building AI-powered user interfaces, such as chat UIs and streaming responses
Familiarity with WebSockets or Server-Sent Events for real-time AI responses
Experience fine-tuning models or with open-source LLMs (Hugging Face, Ollama, vLLM)
Knowledge of MCP (Model Context Protocol) and multi-agent systems
Experience with RabbitMQ, Azure Service Bus or Kafka
Qualifications
Bachelor’s or master’s degree in Computer Science, AI/ML, Data Science, Information Technology or a related field (or equivalent experience)
This guide is for Indian job seekers preparing for Java backend roles, from freshers facing campus and first-job interviews to experienced developers moving into senior positions at product companies and IT services firms. It covers what interviewers ask most in 2025 and 2026 on Java 17 and 21 and Spring Boot 3: OOP, collections, equals and hashCode, streams, exceptions, concurrency and JVM memory, then dependency injection, auto-configuration, REST controllers, validation, JPA and Hibernate, security, microservices and testing. Questions are grouped as easy, medium and hard. Read each answer, compile the code yourself and practise explaining it aloud.
Questions you may be asked
What are the four pillars of OOP, with a Java example of each?
What is the difference between an abstract class and an interface in Java?
What is the difference between method overloading and method overriding?
What is the difference between == and equals() in Java?
