Applied AI Engineer

We are building a centralized AI-driven research and decision-support platform for family offices with exposure to public markets, private markets, and strategic investments. The role involves designing, architecting, and deploying production-grade AI agents that operate across financial research, market intelligence, legal documentation analysis, and talent mapping using state-of-the-art large language models and data systems without developing proprietary foundation models. This is a high-impact applied AI role, comparable to roles in systematic investment firms, quantitative research platforms, and AI-first financial institutions, with direct influence on investment workflows and decision-making.

The Applied AI Engineer will be responsible for end-to-end ownership of AI agents, including: Data acquisition and governance, Data storage architecture, Model orchestration and retrieval pipelines, Agent logic, tooling, and workflow automation, Secure deployment for internal users

The core responsibilities for the job include the following:

AI Agent Architecture and Development:

• Public Markets and Equity Research Agent: Market sizing (global and India), industry structure, and value chain analysis.
• Company-specific research (business models, financials, risks).
• Integration with financial statements, filings, transcripts, and third-party datasets.

Private Markets and Startup Intelligence Agent:

• Sector mapping and TAM/SAM/SOM analysis.
• Startup discovery, peer benchmarking, and trend analysis.
• Founder, investor, and funding history intelligence.
• Analysis of emerging technologies and business models.

Corporate and Legal Intelligence Agent:

• Review, summarize, and compare shareholders' agreements, term sheets, and investment agreements.
• Corporate and commercial contracts.
• Clause-level extraction, deviation analysis, and risk flagging.
• Support compliance and governance review (non-legal advisory support).

Talent and Leadership Intelligence Agent:

• Identification of promoters, CXOs, senior management, and key executives.
• Aggregation of data from public and proprietary sources.
• Structured profiling and comparative analysis.

Data Engineering and Knowledge Systems:

• Design data pipelines for structured data (financials, databases, tabular datasets), semi-structured data (CSV, Excel, APIs), and unstructured data (PDFs, filings, websites, reports).
• Decide what data to store, how to store it, and retention logic.
• Implement and manage: Vector databases (e. g., FAISS, Pinecone, Weaviate, Chroma), relational and document databases, and cloud or secure on-prem storage.
• Ensure data quality through cleaning, normalization, tagging, and version control.

LLM Integration and Orchestration:

• Build agents using existing LLMs (e. g., OpenAI, Gemini, Claude, and cloud-hosted models).
• Implement: Retrieval-Augmented Generation (RAG), prompt engineering for finance, legal, and research domains, and tool-using agents (search, parsing, computation, and extraction).
• Develop multi-step and multi-agent workflows where appropriate.
• Optimize for accuracy, explainability, latency, and cost efficiency.

Governance, Security, and Reliability:

• Implement access control and role-based permissions.
• Ensure confidentiality of financial and legal data.
• Build logging, audit trails, and error handling into agent workflows.
• Maintain documentation and versioning of prompts, pipelines, and agents.

Deployment and Internal Enablement:

• Deliver AI agents that are: Robust and production-ready.
• Usable by non-technical investment professionals.
• Collaborate with stakeholders to refine requirements.
• Provide onboarding, documentation, and knowledge transfer.
• Continuously iterate based on real-world usage and feedback.