Lead AI Engineer

Job Description :Avendus is a leader in financial services, offering bespoke solutions in asset management, credit solutions, investment banking, and wealth management. Our mission is to drive innovation, helping entrepreneurs, wealth creators, and industry pioneers surpass their potential. With a global presence spanning eleven cities across four countries, we blend international perspectives with deep domain expertise to tackle complex challenges and unlock opportunities for growth. For more information, visit avendus.com.We build and ship real-world, production-grade Generative AI systems that directly impact decision-making in financial services. Our work spans Equity Research to get market insights and trends, Portfolio Review engines that generate personalized insights and a Smart Workspace enabling intelligent enterprise search across documents, data lakes, and conversations.If you are excited by owning and leading end-to-end GenAI products, solving complex financial problems, and seeing your models drive measurable business outcomes at scale - this is the place to do it. You will get to work on meaningful GenAI problems, build systems that go beyond demos, and help shape how AI gets applied in real-world enterprise environments. We are looking for someone who likes to build, iterate fast, and own outcomes.Key Responsibilities :- Own and Lead Enterprise grade multiple GenAI projects working with various stakeholders like Data Team and Tech Partners.- Creating a playbook of designing, building and deploying AI Solutions at scale.- Design and optimize RAG pipelines including ingestion, chunking, embeddings, retrieval, reranking, and grounded response generation.- Develop robust prompt engineering strategies to improve response quality, reliability, and task performance.- Work on fine-tuning or model adaptation to improve model behavior for domain-specific use cases.- Build Agentic AI workflows involving tools, APIs, memory, reasoning chains, and multi-step execution.- Build, test, and deploy production-ready GenAI applications for real business use cases.- Use orchestration frameworks/platforms to manage LLM workflows, tool calling, and multi-agent coordination.- Integrate GenAI solutions with enterprise applications, internal systems, and cloud services.- Evaluate model quality, latency, hallucination risks, safety, and cost-performance trade-offs.- Collaborate closely with product, engineering, and business teams to rapidly move from use case identification to deployment.Requirements :- 5 to 7 years of experience in AI/ML engineering, applied AI, or intelligent application development.- At least 2 years of hands-on experience in Generative AI.- Proven track record of delivering at least one GenAI solution to production.- Solid AI/ML fundamentals, strong engineering depth, and practical experience in building applications using LLMs, RAG, Prompt Engineering, Model fine-tuning, Agentic workflows, and orchestration frameworks.- Experience using AWS GenAI services.- Strong coding skills in Python and experience with modern AI application frameworks.- Good understanding of LLM application design, evaluation, observability, and deployment challenges.- Exposure to enterprise AI architecture, security, and responsible AI practices.- Experience with vector databases, semantic retrieval, and embeddings.- Familiarity with LLMOps / MLOps, monitoring, and governance. (ref:hirist.tech)