Must Have

Junior Applied AI Engineer – LLM & Agentic AI Systems

Bangalore (On-site)

About The Role

Building and scaling production-grade AI systems that enable intelligent automation, document understanding, and AI-powered workflows. As organisations increasingly adopt Large Language Models (LLMs) and AI agents, there is a growing need for reliable AI systems that can process complex information, improve decision-making, and deliver accurate, scalable outcomes.

As a Junior Applied AI Engineer, you'll work closely with senior engineers, product teams, and cross-functional stakeholders to develop and optimise AI-powered applications. This is a high-ownership engineering role where you'll contribute to building LLM-based features, retrieval systems, agentic workflows, and AI infrastructure while gaining hands-on experience with modern AI technologies.

What You'll Do

• Build and enhance AI features using transformer-based models, LLM APIs, and prompt engineering techniques for intelligent workflows such as summarisation, extraction, comparison, and generation.
• Contribute to agentic AI systems involving tool calling, multi-step reasoning, workflow orchestration, and state management.
• Design and improve retrieval pipelines including document chunking, embeddings, semantic search, hybrid retrieval, and reranking strategies.
• Build retrieval-augmented generation (RAG) systems that deliver accurate and context-aware AI responses.
• Develop and maintain Python-based AI services, APIs, and backend components supporting production AI applications.
• Improve AI system performance through prompt optimisation, caching, evaluation, latency improvements, and cost optimisation.
• Create evaluation frameworks, test datasets, and quality measurement pipelines to improve AI reliability and reduce hallucinations.
• Support deployment, monitoring, debugging, and continuous improvement of AI systems in production environments.
  
  

What We're Looking For

Must Have

• Up to 3 years of experience in software engineering, machine learning engineering, or applied AI engineering roles.
• Hands-on experience building applications using LLM APIs such as GPT, Claude, Gemini, Llama, or similar models.
• Strong Python programming skills with understanding of software engineering best practices including testing, version control, and code quality.
• Experience with prompt engineering, context management, structured outputs, or function/tool calling.
• Understanding of Retrieval-Augmented Generation (RAG), embeddings, semantic search, and vector database concepts.
• Understanding of AI agent architectures including ReAct-style workflows, tool usage, state management, and multi-step reasoning.
• Experience building or contributing to AI evaluation workflows, quality testing, or model output assessment.
• Foundational understanding of transformer architectures, embeddings, and modern language models.
• Familiarity with APIs, asynchronous programming, and backend frameworks such as FastAPI.
• Strong problem-solving skills and ability to work in a fast-paced environment with evolving priorities.
• High ownership mindset with a focus on learning, execution, and delivering impactful AI solutions.
  
  

Nice to Have

• Experience with agentic AI frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, or similar tools.
• Experience working with document processing, PDF extraction, OCR pipelines, or unstructured text processing.
• Exposure to vector databases such as Pinecone, Weaviate, Qdrant, or pgvector.
• Experience with Docker, CI/CD pipelines, cloud platforms, or AI deployment workflows.
• Familiarity with Kubernetes, observability tools, monitoring systems, and production AI infrastructure.
• Experience with AI evaluation frameworks, synthetic data generation, A/B testing, or experimentation workflows.