GenAI Engineer at HELLA GmbH & Co. KGaA.

Pune, maharashtra, India -

Full Time

Start Date

Immediate

Expiry Date

01 Sep, 26

Salary

0.0

Posted On

03 Jun, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Generative AI, Large Language Models, Azure OpenAI Services, Prompt Engineering, Python, SQL, RAG Architecture, Vector Databases, Model Context Protocol, Agentic AI Frameworks, Docker, Git, Azure AI Search, Azure Machine Learning, Linux, Responsible AI

Industry

Motor Vehicle Manufacturing

Description

GenAI Engineer Location Pacesetting. Passionate. Together. HELLA, one of the leading automotive suppliers worldwide, has shaped the industry with innovative lighting systems and vehicle electronics. In addition, the company is one of the most important partners of the aftermarket and independent workshops. What motivates us: Shaping the mobility of tomorrow and fostering the central market trends such as autonomous driving, efficiency and electrification, connectivity and digitization as well as individualization. Every day, 36,000 employees worldwide are committed to this with passion, know-how and innovative strength. YOUR TASKS About the Role We are looking for a passionate and hands-on Generative AI (GenAI) Engineer to join our team. You will work on designing, developing, and deploying AI-powered solutions leveraging Large Language Models (LLMs) and Azure OpenAI Services. This role requires both strong technical skills and creativity in applying AI to solve real-world business challenges. Key Responsibilities Design, develop, and deploy Generative AI applications using LLMs and Azure OpenAI Services. Implement prompt engineering, vector database integrations, and agentic AI workflows. Work with Azure AI Services including Azure OpenAI, Azure AI Search (Cognitive Search), Azure AI Document Intelligence, Azure AI Content Safety, Azure Cognitive Services (Vision, Language, Speech), Azure Machine Learning, and Azure Blob Storage for end-to-end AI solution development. Design and integrate Model Context Protocol (MCP) servers to extend LLM capabilities with external tools, APIs, and enterprise data sources; build custom MCP servers using Python SDKs for agentic workflows. Develop scalable data processing and model-serving pipelines in Python. Write efficient SQL queries for data extraction, transformation, and analysis. Manage code repositories using Git and containerize applications with Docker. Optimize AI workflows for performance, scalability, and cost-efficiency. Collaborate with cross-functional teams including data engineers, software developers, and product managers. Required Skills & Qualifications 1-3 years of experience in data science, AI/ML development, or related roles. Min. 1 year Hands-on experience with Generative AI and LLMs (e.g., GPT, Azure OpenAI, Hugging Face). Knowledge of prompt engineering techniques, agentic AI frameworks (e.g. CrewAI, MS AutoGen, LangGraph, LangChain), and inter-agent protocols including Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication patterns. Knowledge of retrieval Augmented Generation (RAG) architecture. Practical understanding of Model Context Protocol (MCP): building or consuming MCP servers to connect LLMs with tools, databases, and APIs; familiarity with MCP server lifecycle, resource exposure, and tool definitions. Experience with Vector Databases (e.g., Azure AI Search, Milvus, Pinecone, Weaviate, ChromaDB) for building semantic search and RAG pipelines. Hands-on experience with Azure AI Services: Azure OpenAI (deployments, fine-tuning, embeddings), Azure AI Search with semantic ranking, Azure AI Content Safety for guardrails, Azure AI Document Intelligence for structured data extraction, and Azure Blob Storage for data ingestion pipelines. Strong programming skills in Python and SQL. Experience with Git, Docker, and working in Linux environments. Understanding of safety guardrails and responsible AI practices for LLM applications, including content filtering, prompt injection defense, output validation, and use of Azure AI Content Safety or similar tools. Good to Have Knowledge of Sinequa tool for developing GenAI applications. Experience with CI/CD pipelines for ML/AI deployments. Exposure to LLMOps best practices: prompt versioning, experiment tracking (MLflow, Azure ML), model evaluation frameworks (RAGAS, TruLens), and AI observability tools (Langfuse, Arize, Promptflow). Familiarity with Azure cloud-native AI architectures including Azure Functions, Azure Container Apps, Azure API Management for AI gateways, and Azure Monitor / Application Insights for GenAI workload observability. Experience building or consuming MCP servers for enterprise tool integration (e.g., connecting LLMs to internal databases, ERP/CRM systems, or IoT data streams via MCP). Awareness of emerging AI trends: multimodal LLMs (Azure AI Vision + GPT-4o), small language models (SLMs) for edge/on-premise inference (Phi-3/Phi-4), and AI agent orchestration patterns. Soft Skills Problem-solving mindset with a passion for learning new AI technologies. Strong communication skills to explain technical concepts to non-technical stakeholders. Ability to work in a fast-paced, collaborative, and innovative environment. Team player. YOUR QUALIFICATIONS B.E/B.Tech in computer science/ Information Technology/ Electronics/ Electronics & Communication or related field from a reputed institute 2 to 5 years of industry experience in GenAI Application development and deployment in enterprise applications. Fluent in spoken and written English Take the opportunity to reveal your potential within a global, family-run company that offers you the best possible conditions for progressing in your career. Please send us your application through our careers portal, citing reference number req18215. HELLA India Automotive Pvt Ltd. Ashwini Mankar

Responsibilities

Design, develop, and deploy Generative AI applications using LLMs and Azure OpenAI Services. Implement agentic AI workflows, RAG architectures, and integrate MCP servers to extend LLM capabilities with enterprise data.