Experience:

• 3 to 8 years of experience in software engineering, AI engineering, or Generative AI development
• Experience preferably in startup environments
• Proven experience independently owning projects end-to-end from design to deployment and maintenance

Qualification:

• B.E./B.Tech. in Computer Science or related engineering discipline from premier institutions (IITs, IISc, NITs, BITS Pilani, or top-tier global universities)

Responsibilities:

• Designing, building, and deploying production-grade Generative AI systems for mortgage operations
• Working across LLM applications, AI agents, retrieval systems, reasoning workflows, backend services, APIs, and cloud infrastructure
• Transforming complex mortgage workflows into reliable AI products
• Rapidly converting business problems into scalable AI solutions with minimal supervision
• Building AI agents that automate mortgage underwriting, quality control, compliance, and document review
• Developing RAG-based knowledge systems for reasoning across mortgage documents
• Creating intelligent workflows combining LLM reasoning with deterministic business rules
• Building production-grade AI APIs and backend services
• Developing evaluation pipelines to improve AI quality, accuracy, latency, and cost

Additional responsibilities:

• Design scalable, secure, and production-ready AI architectures
• Strong debugging skills and systems thinking
• Ownership mindset with ability to move quickly in an early-stage startup

Nice to have:

• Experience building AI copilots, autonomous agents, or enterprise AI assistants
• Familiarity with MCP, AI tool integration, and agent orchestration
• Experience fine-tuning, distillation, or evaluation of open-source LLMs
• Knowledge of AI safety, governance, and responsible AI practices
• Experience working with document-heavy enterprise domains such as financial services, banking, insurance, healthcare, legal, or mortgage technology
• Experience deploying AI applications on AWS, Azure, or GCP

More skills:

Python, modern backend development, Large Language Models (LLMs), multi-agent workflows, function/tool calling, structured outputs, Retrieval-Augmented Generation (RAG), semantic search, integration of commercial and open-source foundation models (OpenAI, Anthropic, Gemini, Llama, Mistral), AI pipeline frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen), model evaluation, hallucination mitigation, guardrails, prompt optimisation, LLM observability, OCR, document intelligence, structured information extraction, multimodal AI systems, APIs, databases, cloud infrastructure, Docker, Kubernetes, CI/CD pipelines

Other:

• Full-time in-office role based in Bangalore
• Work on AI systems that understand complex documents, synthesize information, explain decisions, identify exceptions, and improve through continuous learning and expert feedback