Generative AI Solutions Engineer

About The Opportunity

• Architect, prototype, and deploy GenAI applications (LLMs, RAG, multimodal) on Azure OpenAI, Cognitive Search, and Kubernetes-based microservices.
• Build and orchestrate agentic frameworks (LangChain, AutoGen) for multi-agent reasoning, tool-calling, and end-to-end workflow automation.
• Engineer low-latency, high-throughput data and prompt pipelines using Azure Data Factory, Event Hub, and Cosmos DB.
• Optimize model performance and cost via fine-tuning, quantization, scalable caching on Azure ML and AKS.
• Implement production-grade CI/CD, observability (App Insights, Prometheus), security, and responsible-AI guardrails.
• Collaborate cross-functionally with product, design, and customer success teams to deliver measurable business impact.
  

Skills & Qualifications

• 3-5 years hands-on Generative AI/LLM engineering (GPT, Llama 2, Claude) with at least one solution in production.
• Proficiency with Microsoft Azure services: Azure OpenAI, Functions, Data Factory, Cosmos DB, AKS.
• Strong Python & TypeScript skills with experience in agentic frameworks (LangChain, AutoGen, Semantic Kernel) and REST/GraphQL APIs.
• Solid foundation in cloud MLOps: Docker, Helm, Terraform/Bicep, GitHub Actions or Azure DevOps.
• Proven ability to optimize end-to-end GenAI pipelines for performance, cost efficiency, and reliability.
  

Preferred

• Experience scaling GenAI pipelines to >10 K QPS using vector databases (Pinecone, Qdrant) and distributed caching.
• Familiarity with prompt engineering, fine-tuning methodologies, and retrieval-augmented generation best practices.
• Knowledge of Kubernetes operators, Dapr, and service mesh patterns for resilient microservices.
  

• Competitive salary and flexible hybrid work model in Pune and Mumbai offices.
• Rapid career growth within a pioneering AI leadership team.
• Collaborative, innovation-driven culture emphasizing ethical and responsible AI.