Join our DEX India team as AI Context Engineer to design, build, and maintain the systems that supply high-quality, relevant context to LLMs and AI agents. you'll own the ingestion, transformation, retrieval, and evaluation pipelines that turn raw data into reliable context (embeddings, indexes, metadata) used by generative AI products. This role sits at the intersection of engineering, data, and applied ML ideal for engineers who enjoy systems design, information retrieval, prompt engineering, and productionizing AI.
Key Responsibilities
-
Implement context-aware pipelines that assemble and structure information for LLMs and other AI models, ensuring accurate and safe responses.
- Design and implement scalable pipelines to ingest, normalize, and enrich structured and unstructured data.
- Define and implement metadata schemas, chunking strategies, and relevance heuristics to enhance retrieval quality and cost-efficiency.
-
Integrate LLMs with retrieval components (RAG), caching layers, and orchestration logic to deliver context-aware responses.
-
Collaborate with product, ML, and platform engineering teams to translate product requirements into context models and SLAs.
- Develop and enforce AI governance frameworks, focusing on ethical, legal, and compliance standards for responsible AI adoption.
- Analyse complex datasets to inform project direction, technology choices, and business strategies.
- Optimise solutions for cost, latency, and reliability, balancing performance, and accuracy in production environments.
- Document and share guidelines for AI integration, governance, and cloud development across the enterprise.
What You Need to Succeed
- 2-4 years of experience with advanced proficiency in JavaScript, React, Angular, and RESTful API integration.
- Strong programming skills in Python and comfort with Java/TypeScript or similar for integrations.
- Hands-on experience integrating AI/ML features into cloud-based platforms (preferably ServiceNow, Azure, or similar).
- Strong background in Azure (Azure ML, Azure AI, Cognitive Services) and cloud-native architectures.
- Professional experience through internships, projects, or past work related to using LLMs to enhance productivity.
- Experience using Python and frameworks such as Hugging Face, LangChain, PyTorch, or TensorFlow.
- Familiarity with IDEs (e.g., Cursor), APIs, data structures, and JSON.
- Understanding of tokenization, prompt formatting, and context window limits.
- Demonstrated critical and deep-thinking abilities to understand why and explore alternative approaches to achieve goals.
- Excellent communication skills fearless in asking questions to ensure clear understanding and able to simplify complex concepts for less technical audiences.
- Passion for learning and contributing to a collaborative, inclusive team.
