Senior GenAI Engineer

About Senzcraft:Founded by IIM Bangalore and IEST Shibpur Alumni, Senzcraft is a hyper-automation company. Senzcraft vision is to Radically Simplify Today's Work. And Design Business Process For The Future. Using intelligent process automation technologies.We have a suite of SaaS products and services, partnering with automation product companies.Please visit our website - for more detailsOur AI Operations SaaS platform – on linkedin -> is awarded by Analytics India Magazine in it’s report “State of AI in India” as a “Niche AI startup”. Senzcraft is also recognized by NY based SSON as a top hyper-automation solutions provider.About the Role (Senior GenAI Engineer):Role OverviewWe are seeking a highly skilled Senior GenAI Engineer with 5+ years of experience in AI/ML and automation engineering to design, develop, and deploy production-ready Generative AI solutions. This role requires strong hands-on expertise in LLMs, orchestration frameworks, RAG, embeddings, and MCP integration. You will work across both infrastructure and solution design, translating business needs into robust, scalable GenAI applications.Key ResponsibilitiesDesign & Development: Build and deploy GenAI/LLM-powered applications, integrating frameworks such as CrewAI, LangChain, AutoGen, Semantic Kernel, or LlamaIndex.Orchestration & Integration: Develop and maintain Model Context Protocol (MCP) interfaces and servers to enable interoperability across AI/simulation components.RAG & Embeddings: Implement efficient Retrieval-Augmented Generation (RAG) pipelines, vector DB integration (Pinecone, FAISS, Chroma), and embedding strategies.Prompting & Fine-tuning: Apply prompt engineering, model fine-tuning, and optimization techniques to improve GenAI solutions.Application Development: Collaborate with business and application teams to design, prototype, and deploy AI-driven workflows and user-facing features.Production-Readiness: Architect, build, and scale agent-based systems for enterprise use cases, ensuring performance, security, and maintainability.Cloud & Deployment: Deploy AI/ML workloads on AWS, Azure, and GCP, leveraging services like DynamoDB, storage, compute, and container runtimes.Collaboration: Communicate effectively with both technical and non-technical stakeholders to align AI solutions with business goals.Continuous Learning: Stay current with the latest in Generative AI, LLM research, orchestration frameworks, and MLOps/LLMOps practices.QualificationsExperience: 5+ years in AI/ML engineering, including at least 2+ years in GenAI/LLM applications.Programming: Strong proficiency in Python (async, API integration); experience with Java, JavaScript/Node.js, React.js, and front-end technologies is a plus.LLMs & Frameworks: Hands-on experience with OpenAI, Anthropic, Mistral, or similar LLMs; orchestration with LangChain, CrewAI, AutoGen, Semantic Kernel, or LlamaIndex.Vector DBs & RAG: Expertise in embeddings and vector databases (Pinecone, FAISS, Chroma) and retrieval-based architectures.MCP & Agent Systems: Experience with MCP server implementation and building agent-based GenAI solutions.Cloud Platforms: Practical experience deploying AI/ML systems on AWS, Azure, or GCP.Version Control: Strong understanding of Git and collaborative SDLC practices.MLOps/LLMOps: Knowledge of CI/CD, monitoring, and ML/LLM operationalization best practices.Nice to Have: Database expertise (SQL, NoSQL, DynamoDB), containerization (Docker/Kubernetes), Infra-as-Code (Terraform), and experience with front-end integrations.What Success Looks LikeDelivery of scalable, production-ready GenAI solutions with measurable impact on business workflows.Demonstrated ability to translate business problems into structured ML/GenAI solutions.Strong collaboration across product, engineering, and business teams.Continuous improvement in solution performance, reliability, and user adoption.