Senior Generative AI / Agentic AI Engineer

Overview

Lead the design, development and deployment of production-grade generative AI and agentic AI solutions, delivering secure, scalable, business-oriented AI systems that operate on structured and unstructured data.

What you'll do

• Lead the design, development, and deployment of scalable applications using Python or .NET.
• Architect and implement Generative AI solutions, including RAG systems, LLM pipelines, prompt engineering, and model fine-tuning.
• Work with Knowledge Graph technologies to model, organize, and connect enterprise data.
• Design cloud-native applications using Azure services such as Azure Functions, App Services, Azure AI Search, Cosmos DB, AKS, Azure OpenAI, Service Bus, Event Hub, and Storage.
• Oversee the end-to-end technical delivery of projects, ensuring adherence to best practices, security, and performance standards.
• Collaborate with product owners, architects, and cross-functional teams to define technical roadmaps.
• Manage and mentor engineering teams (5–15 members), including task planning, code reviews, and skill development.
• Ensure high-quality coding standards and maintain CI/CD pipelines.
• Troubleshoot and optimize distributed systems and cloud deployments.
• Communicate project updates, risks, and technical decisions to stakeholders.
• Transform data using Databricks (PySpark/SQL), with a basic understanding of batch and streaming ingestion.

What you'll need

• 10–12+ years of overall industry experience with at least 2–4 years in a Gen AI technical lead or team lead role.
• Strong development experience in Python or .NET (one primary, familiarity with the other is a plus).
• Solid hands-on experience with Generative AI and LLM-based systems (OpenAI, Azure OpenAI, Hugging Face, Llama, Phi, LangChain, Semantic Kernel, etc.).
• Strong Python and Azure engineering expertise with hands-on experience in FastAPI and Azure Functions, asynchronous and batch processing, and integration with Azure services including Blob Storage, Cosmos DB, Azure AI Search, Azure OpenAI, Event Hub, Logic Apps, and Durable Functions.
• Proven ownership of end-to-end GenAI platforms, covering RAG pipelines, document intelligence, embedding generation and management, vector and graph database integrations, semantic search, and AI governance, with the ability to design, deploy, and operate enterprise-ready GenAI solutions on Azure.
• Good understanding of Knowledge Graphs, graph databases, ontologies, and graph modeling (Neo4j, AWS Neptune, Azure Cosmos DB Gremlin API, RDF, SPARQL, etc.).
• Proven ability to design and deploy scalable, cloud-native solutions on Azure.
• Strong foundational knowledge of the Azure cloud ecosystem (compute, network, data, identity, monitoring, DevOps).
• Experience managing small to medium-sized teams, handling project execution, planning, and delivery.
• Hands-on experience with CI/CD pipelines, Git workflows, and DevOps practices.
• Strong analytical, problem-solving, and decision-making abilities.
• Excellent communication skills with the ability to articulate technical concepts to non-technical stakeholders.
• Experience with vector databases, RAG pipelines, embeddings, and enterprise search.
• Knowledge of MLOps and deploying ML/AI models in production.
• Exposure to microservices architecture and container orchestration (Docker, Kubernetes/AKS).
• Understanding of security best practices in cloud and AI deployments.
• Prior experience working in agile/scrum environments.
• Experience in database design: Cosmos DB (SQL API, indexing, partitioning).
• Azure & AI: Azure OpenAI (Chat Completion, Embeddings, RAG pipelines), Document Intelligence / Form Recognizer, Azure AI Search (indexes, vector search, hybrid search), Azure Cognitive Services (Language, Vision, Speech), Azure Functions (durable and serverless workflows), Azure API Management.

Nice to have

• Familiarity with .NET, in addition to a primary Python background.
• Basic understanding of batch and streaming ingestion, and transforming data using Databricks (PySpark/SQL).
• Upskilling in 2 to 4 weeks, if timeframe permits: CI/CD pipelines, Git workflows, and DevOps practices.
• Exposure to microservices and container orchestration (Docker, Kubernetes/AKS).
• Experience deploying ML/AI models in production (MLOps).

Details

• Location: IN-GJ-Ahmedabad, India, Ognaj (eInfochips).
• Employment type: Full time.
• Job category: Engineering Services.