Applied Gen AI Engineer

Job Description #1: Applied GenAI Engineer

Role Summary
We are seeking Applied GenAI Engineers to solve complex business problems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agentic AI. This is a hands-on individual contributor role where you will take problems from use-case definition to prototype and into production, building secure, governed, and measurable solutions.

Location / Work Model

Locations: US (NYC) ,
Primary Use Cases You Will Support

Data lineage & metadata intelligence
Data controls & governance
Risk / compliance analytics
Tool rationalization & inventory normalization
Operations intelligence & workflow optimization
Onboarding support & document intelligence workflows
Fraud & anomaly detection augmentation
Key Responsibilities

Build and productionize LLM applications: RAG, summarization, extraction, classification, entity resolution, and recommendation.
Design agentic workflows: tool-using agents, multi-step planning, guardrails, and audit logs.
Implement document & data intelligence pipelines: parsing, chunking, embeddings, hybrid retrieval, and re-ranking.
Create evaluation harnesses and quality gates: golden datasets, regression tests, automated scoring, and human review loops.
Implement reliability patterns: hallucination mitigation, grounding, prompt-injection defenses, and safe tool execution.
Engineer solutions with enterprise constraints: security, privacy, access control, observability, and cost/performance optimization.
Collaborate with data engineering and governance stakeholders to align with entitlements, lineage, and controls.
Required Skills & Experience

Strong Python engineering and API development; ability to ship production-grade services.
Hands-on experience with LLMs and common patterns (RAG, tool calling, structured outputs).
Experience building search/retrieval systems (vector + keyword / hybrid) and working with unstructured corpora.
Solid software engineering fundamentals: testing, CI/CD, logging/monitoring, and containerization.
Ability to translate ambiguous business problems into clear technical designs and measurable outcomes.
Nice-to-Have

Knowledge graph exposure (entity linking, semantic search, graph-based context assembly).
Experience in regulated environments (controls, audit, model governance, data privacy).
Familiarity with CyberSecurity , DevSecOps, LLMOps: prompt/version management, evaluation pipelines, monitoring
Comments for Suppliers: