S
Applied AI Engineer/NYC-Hybrid | 3 Days onsite
Suncap Technology
2 hours ago
Full-time
On-site
Applied AI Engineer
Overview
We are seeking a senior, hands-on Applied AI Engineer to support the development of an enterprise GenAI platform within Fixed Income Institutional Lending. The platform supports AI-powered document extraction, enterprise search, embedded assistants, and automated business workflows.
This is a production engineering role-not a research or proof-of-concept position. The ideal candidate combines strong software engineering and system design skills with deep hands-on experience building RAG, retrieval, and GenAI solutions in production. Candidates should be comfortable explaining how their solutions work under the hood, the architectural decisions they made, and how they addressed real-world production challenges.
What You'll Do Design and build production-grade GenAI applications and reusable AI workflows across Lending business lines. Architect and develop RAG and advanced retrieval solutions, including embeddings, vector databases, chunking, semantic/hybrid search, metadata filtering, and re-ranking. Build AI-powered document ingestion and data extraction pipelines with validation, confidence scoring, traceability, and human-in-the-loop review. Develop AI assistants and agentic workflows using tool/function calling, structured outputs, and enterprise data sources. Design scalable AI architectures and make technical decisions around models, retrieval, orchestration, APIs, data flows, and system performance. Establish LLMOps and evaluation practices, including testing, prompt/version management, observability, feedback loops, regression testing, and reliability monitoring. Troubleshoot real production issues including retrieval degradation, hallucinations, model regressions, prompt changes, data quality, and latency. Build AI solutions that meet enterprise requirements for security, entitlements, PII handling, governance, and auditability. Participate in architecture and code reviews and help establish reusable AI engineering standards and platform capabilities. What You Need
5+ years of software engineering experience, with strong hands-on development skills in Python or Java and experience designing enterprise applications. 2+ years of dedicated GenAI experience building and operating AI solutions in a production enterprise environment. Deep hands-on knowledge of RAG architecture and retrieval systems-not simply high-level familiarity with GenAI concepts. Strong understanding of embeddings, vector databases, chunking, semantic search, hybrid search, metadata filtering, and re-ranking. Experience with advanced retrieval techniques such as multi-stage/multi-vector retrieval, late-interaction approaches (e.g., ColBERT), and retrieval evaluation. Strong architecture and system design skills with the ability to explain technical decisions, trade-offs, and implementation details. Experience building AI solutions from the ground up, rather than primarily consuming third-party APIs or prebuilt AI solutions. Hands-on experience with RAG, agentic workflows, tool/function calling, structured outputs, and GenAI orchestration frameworks. Strong LLMOps experience, including evaluation frameworks, prompt/version management, regression testing, observability, monitoring, and feedback loops. Experience building AI-driven document ingestion/extraction pipelines with measurable accuracy and quality. Experience supporting production AI systems and resolving issues involving model behavior, retrieval quality, prompts, data quality, reliability, or performance. Ability to discuss technical implementations under the hood, reason through technical problems, and clearly defend architecture decisions. Experience applying AI to real enterprise business use cases such as document intelligence, enterprise search, reconciliation, contracts/credit agreements, or natural-language-to-data applications. Experience with financial services, Fixed Income, Institutional Lending, regulated environments, enterprise security/data governance, React/Angular, or reusable AI platforms is preferred.
Overview
We are seeking a senior, hands-on Applied AI Engineer to support the development of an enterprise GenAI platform within Fixed Income Institutional Lending. The platform supports AI-powered document extraction, enterprise search, embedded assistants, and automated business workflows.
This is a production engineering role-not a research or proof-of-concept position. The ideal candidate combines strong software engineering and system design skills with deep hands-on experience building RAG, retrieval, and GenAI solutions in production. Candidates should be comfortable explaining how their solutions work under the hood, the architectural decisions they made, and how they addressed real-world production challenges.
What You'll Do Design and build production-grade GenAI applications and reusable AI workflows across Lending business lines. Architect and develop RAG and advanced retrieval solutions, including embeddings, vector databases, chunking, semantic/hybrid search, metadata filtering, and re-ranking. Build AI-powered document ingestion and data extraction pipelines with validation, confidence scoring, traceability, and human-in-the-loop review. Develop AI assistants and agentic workflows using tool/function calling, structured outputs, and enterprise data sources. Design scalable AI architectures and make technical decisions around models, retrieval, orchestration, APIs, data flows, and system performance. Establish LLMOps and evaluation practices, including testing, prompt/version management, observability, feedback loops, regression testing, and reliability monitoring. Troubleshoot real production issues including retrieval degradation, hallucinations, model regressions, prompt changes, data quality, and latency. Build AI solutions that meet enterprise requirements for security, entitlements, PII handling, governance, and auditability. Participate in architecture and code reviews and help establish reusable AI engineering standards and platform capabilities. What You Need
5+ years of software engineering experience, with strong hands-on development skills in Python or Java and experience designing enterprise applications. 2+ years of dedicated GenAI experience building and operating AI solutions in a production enterprise environment. Deep hands-on knowledge of RAG architecture and retrieval systems-not simply high-level familiarity with GenAI concepts. Strong understanding of embeddings, vector databases, chunking, semantic search, hybrid search, metadata filtering, and re-ranking. Experience with advanced retrieval techniques such as multi-stage/multi-vector retrieval, late-interaction approaches (e.g., ColBERT), and retrieval evaluation. Strong architecture and system design skills with the ability to explain technical decisions, trade-offs, and implementation details. Experience building AI solutions from the ground up, rather than primarily consuming third-party APIs or prebuilt AI solutions. Hands-on experience with RAG, agentic workflows, tool/function calling, structured outputs, and GenAI orchestration frameworks. Strong LLMOps experience, including evaluation frameworks, prompt/version management, regression testing, observability, monitoring, and feedback loops. Experience building AI-driven document ingestion/extraction pipelines with measurable accuracy and quality. Experience supporting production AI systems and resolving issues involving model behavior, retrieval quality, prompts, data quality, reliability, or performance. Ability to discuss technical implementations under the hood, reason through technical problems, and clearly defend architecture decisions. Experience applying AI to real enterprise business use cases such as document intelligence, enterprise search, reconciliation, contracts/credit agreements, or natural-language-to-data applications. Experience with financial services, Fixed Income, Institutional Lending, regulated environments, enterprise security/data governance, React/Angular, or reusable AI platforms is preferred.