Senior Software Engineer - Generative AI

About the RoleWe are looking for a highly skilled Senior Software Engineer with deep, hands-on experience in Generative AI, large language models (LLMs), and modern ML systems. This is an end-to-end engineering role: you will design, build, and deploy AI-driven systems while working closely with founders, clients, and cross-functional teams. At Newtuple, engineers work across multiple problem domains, from real-time voice agents to RAG systems, on-prem LLM deployments, workflow automation, and large-scale enterprise AI applications. You’ll take ideas from prototype to production in weeks, not months, and operate in an environment that rewards ownership, speed, and innovation. A key expectation for this role is comfort with AI-assisted development, including the use of AI coding tools, agents, automated refactoring workflows, and LLM-driven engineering assistance. We want engineers who actively leverage AI to accelerate development. ResponsibilitiesGenAI DevelopmentDesign, develop, and deploy GenAI-based applications including RAG systems, retrieval pipelines, LLM-powered workflows, evaluation tools, and production agents.Ability to quickly prototype AI applications as well as develop for production scaleSoftware EngineeringArchitect and implement high-performance backend systems in Python, Node.js, or similar languages.Build reliable, maintainable microservices, APIs, and full pipelines that support AI features end-to-end.Convert loosely defined ideas and client requirements into production-quality systems through rapid prototyping and iteration.Work across multiple projects and adapt quickly to new domains and technical stacks. LLMOps & DeploymentImplement CI/CD pipelines, model monitoring, evaluation dashboards, and end-to-end model lifecycle workflows.Deploy and scale AI systems on cloud platforms (AWS, GCP, Azure).Optimize compute cost, latency, and performance across both training and inference. Research & InnovationStay up to date with the latest advancements in GenAI, multimodal models, vector databases, and agent frameworks.Experiment with and evaluate open-source models such as LLaMA, Mistral, DeepSeek, and others.Explore autonomous AI agents, orchestration frameworks, and emerging tooling that improves developer productivity. Requirements: Must-Have Skills4+ years of full-time software engineering experience, including 1–2 years working directly with LLMs or applied ML.Strong command of Python, ML frameworks (PyTorch/TensorFlow), and LLM tooling (Transformers, LangChain, LlamaIndex, etc.).Hands-on experience building RAG pipelines, using embeddings, vector databases (FAISS, Pinecone, Milvus), or fine-tuning LLMs.Proven experience deploying production-grade AI applications.Solid understanding of algorithms, data structures, system architecture, and API design.Comfort using AI coding assistants and AI agents to accelerate development, including code generation, refactoring, testing, and multi-step reasoning automation.Ability to operate independently in ambiguous environments and convert rough requirements into working solutions.Strong generalist skills: backend engineering, cloud services, data workflows, experimentation, and research. Good-to-HaveExperience with multi-agent systems (OpenAI Agents SDK, Claude Agents SDK, CrewAI, LangGraph, others).Familiarity with multimodal AI (Vision/Audio models).Knowledge of distributed systems and high-performance computing.Experience working in a startup or fast-paced consulting environment. What We OfferOpportunity to work with a cutting-edge Generative AI company based in Pune.Ownership of key AI initiatives and full-stack responsibility from prototype to production.Direct collaboration with founders and exposure to a wide variety of domains: HRTech, Retail, Surveillance, Finance, Healthcare, and more.A fast-paced environment where experimentation, rapid delivery, and solving real problems for real customers is the norm.Growth paths into Tech Lead, AI Architect, or other roles as the company scales.