Artificial Intelligence Engineer

AI Engineer

Amunra Advisors LLP About Us Amunra is an India-focused quantitative investment and market intelligence platform. Our work sits across systematic investing, Indian derivatives, market microstructure, risk management, AI, and data infrastructure. We use market data, positioning data, macro data, news, regulatory information, and research material to support quantitative research, portfolio monitoring, risk systems, and internal intelligence tools. We are looking for an AI Engineer to help build Amunra’s internal knowledge systems, including knowledge graphs, second-brain tools, AI-powered research assistants, and intelligent information retrieval systems.

Role Overview The AI Engineer will be responsible for building AI-powered knowledge infrastructure that helps Amunra organise, connect, search, and reason over internal and external information. This role will focus on creating a “second brain” for the firm: a system that connects research notes, market data, entities, instruments, companies, sectors, macro events, regulatory information, news, documents, and internal knowledge into a structured and searchable intelligence layer. The role is suited for someone who is strong in Python, experienced with AI systems, comfortable working with structured and unstructured data, and interested in knowledge graphs, LLMs, retrieval systems, and financial markets.

Key Responsibilities Build Knowledge Graph and Second Brain Systems

• Design and build knowledge graph systems that connect entities, documents, events, markets, instruments, companies, sectors, themes, and research material
• Develop internal second-brain tools to help teams capture, organise, retrieve, and reuse knowledge
• Create entity and relationship models that make internal knowledge easier to search, analyse, and reason over
• Build systems that connect structured data, unstructured documents, research notes, market information, and metadata

Build AI-Powered Research and Intelligence Tools

• Build AI assistants, search tools, summarisation workflows, and question-answering systems for internal use
• Develop tools that help researchers discover relationships, track market events, summarise documents, and extract insights
• Use LLMs, embeddings, retrieval-augmented generation, and semantic search to improve access to internal knowledge
• Improve the accuracy, traceability, and usefulness of AI-generated outputs

Work with Structured and Unstructured Data

• Process research notes, news, regulatory filings, market commentary, internal documents, macro data, and financial datasets
• Extract entities, relationships, events, tags, themes, and metadata from unstructured information
• Create pipelines for document ingestion, classification, enrichment, retrieval, and linking
• Work with data engineers to ensure knowledge systems are connected to reliable data sources

Develop Knowledge Infrastructure

• Work with graph databases, vector databases, relational databases, and metadata systems
• Build pipelines to keep knowledge graphs and second-brain systems updated as new information arrives
• Design schemas, ontologies, taxonomies, and tagging systems for financial and research-related knowledge
• Maintain data quality, entity resolution, deduplication, versioning, and lineage across knowledge systems

Build Production-Ready AI Systems

• Build backend services, APIs, workflows, and integrations for AI and knowledge tools
• Deploy and monitor AI-powered systems in production environments
• Implement logging, evaluation, feedback loops, access controls, and error handling
• Ensure systems are scalable, secure, auditable, and maintainable

Required Skills

• Strong hands-on experience with Python
• Experience building AI, LLM, search, retrieval, or knowledge-based applications
• Experience working with structured and unstructured data
• Understanding of knowledge graphs, entity relationships, metadata, taxonomies, or ontologies
• Experience with data extraction, classification, tagging, or entity mapping
• Experience working with APIs, databases, backend services, and production systems
• Ability to clean, organise, and connect messy real-world information
• Experience using Git and working in Linux-based environments
• Strong problem-solving skills and ability to work with research, data, and engineering teams

Preferred Skills

• Experience with graph databases such as Neo4j, Memgraph, Amazon Neptune, or similar
• Experience building knowledge graphs, second-brain systems, research knowledge bases, or entity-linking systems
• Experience with LLM frameworks and tools such as LangChain, LlamaIndex, OpenAI API, Anthropic API, Hugging Face, or similar
• Experience with vector databases such as Pinecone, Weaviate, Milvus, Chroma, FAISS, pgvector, or similar
• Experience with retrieval-augmented generation, semantic search, embeddings, ranking, or document search
• Experience with document processing, information extraction, OCR, summarisation, or classification
• Experience with metadata systems, data catalogues, knowledge management tools, or research intelligence platforms
• Experience with AWS or cloud-based infrastructure
• Experience with financial markets, macro data, news, regulatory information, research workflows, or investment-related systems

Ideal Candidate The ideal candidate is curious, structured, and comfortable building systems that turn scattered information into connected intelligence. They should be able to think in entities, relationships, documents, events, and workflows. They should enjoy building tools that help researchers and teams retrieve knowledge, discover connections, and make better decisions. Financial-market experience is preferred, but strong ability in AI systems, knowledge graphs, information architecture, and production engineering is more important.