Prompt Engineer Jobs in Rochester, NY (NOW HIRING)

GenAI Solutions Developer - Senior Consultant

Deloitte's Audit & Assurance professionals help organizations navigate business risks and opportunities-across financial, operational, information technology (IT), business, and regulatory areas-to build resilience and accelerate performance. In this role, you'll design and deliver end-to-end Generative AI (GenAI) solutions - including Retrieval-Augmented Generation (RAG) multi-agent orchestration, real-time AI task pipelines, and knowledge graph-powered reasoning-that are scalable, secure, and aligned to enterprise governance expectations.

Recruiting for this role ends on May 31st 2026.

Work you'll do

       Lead business and technical requirements elicitation with client stakeholders; own end-to-end gap analysis; translate needs into solution architecture, detailed technical specifications, and delivery-ready backlog artifacts.

• Design, build, test, and deploy GenAI application platforms-comprising Python/FastAPI AI microservices, Node.js backend APIs, and React frontends-using asynchronous task orchestration (Redis pub/sub, Server-Sent Events) to deliver real-time AI workflows at enterprise scale; ensure non-functional requirements (security, performance, reliability, observability) are met.
• Own end-to-end retrieval-augmented generation (RAG) implementations (ingestion, chunking, embedding, indexing, retrieval, orchestration); define prompt engineering standards and evaluation harnesses to measure quality and reduce hallucinations.
• Architect agentic AI workflows using LangChain and LangGraph (tool-using agents, multi-step orchestration, parallel multi-agent patterns); integrate LLM pipelines with knowledge graphs (Neo4j) for structured reasoning over audit and compliance data; implement human-in-the-loop checkpoints, auditability controls, and enterprise governance guardrails.
• Evaluate and integrate frontier LLMs (Gemini 2.5 Pro/Flash, Claude, GPT-4o) and specialized models; define LLM selection criteria, cost/latency tradeoffs, and quality benchmarks; run prompt iteration cycles and structured output evaluation to meet acceptance criteria across audit-specific use cases.
• Own API and integration service design using FastAPI and Express; deliver scalable RESTful interfaces and streaming endpoints (Server-Sent Events); coordinate integration with downstream/upstream enterprise systems, Microsoft Azure AD identity and access management (IAM), and AI task monitoring pipelines.
• Design and deliver data engineering pipelines to curate governed datasets for GenAI solutions-including document parsing, structured extraction, and embedding preparation; partner with data governance and risk teams on lineage, access controls, and data quality standards for AI model inputs.
• Operationalize GenAI application deployments using containerized patterns (Docker, Kubernetes, Helm); implement monitoring and observability for AI workloads (performance, cost, model drift, output quality signals) and drive continuous improvement through incident learnings and release management.
• Advise on emerging GenAI models, frameworks, and toolkits (e.g., Gemini 2.5, Claude, LangGraph, Milvus, Neo4j); prototype and recommend options with explicit tradeoffs across audit value, delivery effort, risk, compliance, and total cost of ownership (TCO); guide responsible AI adoption within regulated environments.

       Collaborate with cross-functional teams (product, engineering, data, risk, and stakeholders) to deliver adoption-ready solutions and documentation.

The team
Our team culture is collaborative and encourages team members to take initiative and seek on-the-job learning opportunities. Audit & Assurance services are focused on engagements related to independent External Audit services, Accounting, Controls & Reporting Advisory, and Specialized Assurance & Sustainability. We bring together the diverse skills and industry experience of our people, leading-edge technology, and a global network to deliver high-quality audits of financial statements and internal controls over financial reporting, along with assurance reports and valuable advice and insights across the corporate reporting landscape. Learn more about Deloitte Audit & Assurance.  

Qualifications
Required:

       Bachelor's degree (or equivalent) in Computer Science, Engineering, Data Science, or a related field (advanced degree a plus).

       4+ years of experience in software engineering, full stack development, and/or AI/ML solution delivery.

       Python programming (production-grade) and strong SQL.

       Natural Language Processing (NLP) applied to GenAI solutions.

       Agentic AI design/implementation, including LangChain, LangGraph, and LlamaIndex.

       Hands-on experience with RAG architectures and implementation.

       Strong prompt engineering (design, iteration, and evaluation).

       Experience with vector databases (e.g., Milvus, Pinecone, Chroma, FAISS or similar) and embedding-based retrieval.

       Experience with GenAI model build: training, fine-tuning, and validation; practical LLM evaluation using common metrics.

       Experience with model deployment (serving, monitoring, iteration) and production hardening.

       Experience with containers (e.g., Docker) and scalable runtime patterns.

       Experience building ETL pipelines and data engineering solutions (data quality, preprocessing, and curation).

       API development and integration (RESTful services); backend development using FastAPI (or equivalent).

       Experience integrating multiple LLM provider APIs (OpenAI, Anthropic, Google GenAI/Gemini) using their respective Python SDKs; ability to swap and benchmark models across providers.

       Experience with asynchronous messaging and real-time data patterns (Redis pub/sub, Server-Sent Events, WebSockets) for AI task orchestration and streaming output delivery.

       Experience with cloud AI/ML services with a focus on GCP (Vertex AI, GKE, Cloud Storage, Filestore); familiarity with Azure and AWS AI/ML services a plus.

       You should reside within a commutable distance of your assigned office with the ability to commute daily, if required

       You can expect to co-locate on average 3 times a week with variations based on types of work/projects and client locations

       Ability to travel up to 50%, on average, based on the work you do and the clients/sectors you serve

       Limited immigration sponsorship may be available.

Preferred:

       Experience with deep learning frameworks (e.g., TensorFlow, PyTorch, Keras).

       Familiarity with AI/GenAI ethics, governance, and responsible AI implementation practices.

       Cloud certification (AWS, Azure, or GCP) and/or AI/ML certification.

The wage range for this role takes into account the wide range of factors that are considered in making compensation decisions including but not limited to skill sets; experience and training; licensure and certifications; and other business and organizational needs.  The disclosed range estimate has not been adjusted for the applicable geographic differential associated with the location at which the position may be filled.  At Deloitte, it is not typical for an individual to be hired at or near the top of the range for their role and compensation decisions are dependent on the facts and circumstances of each case.  A reasonable estimate of the current range is $124,658 to $179,431.

You may also be eligible to participate in a discretionary annual incentive program, subject to the rules governing the program, whereby an award, if any, depends on various factors, including, without limitation, individual and organizational performance.

GenAI Solutions Developer - Senior Consultant

Deloitte's Audit & Assurance professionals help organizations navigate business risks and opportunities-across financial, operational, information technology (IT), business, and regulatory areas-to build resilience and accelerate performance. In this role, you'll design and deliver end-to-end Generative AI (GenAI) solutions - including Retrieval-Augmented Generation (RAG) multi-agent orchestration, real-time AI task pipelines, and knowledge graph-powered reasoning-that are scalable, secure, and aligned to enterprise governance expectations.

Recruiting for this role ends on May 31st 2026.

Work you'll do

       Lead business and technical requirements elicitation with client stakeholders; own end-to-end gap analysis; translate needs into solution architecture, detailed technical specifications, and delivery-ready backlog artifacts.

• Design, build, test, and deploy GenAI application platforms-comprising Python/FastAPI AI microservices, Node.js backend APIs, and React frontends-using asynchronous task orchestration (Redis pub/sub, Server-Sent Events) to deliver real-time AI workflows at enterprise scale; ensure non-functional requirements (security, performance, reliability, observability) are met.
• Own end-to-end retrieval-augmented generation (RAG) implementations (ingestion, chunking, embedding, indexing, retrieval, orchestration); define prompt engineering standards and evaluation harnesses to measure quality and reduce hallucinations.
• Architect agentic AI workflows using LangChain and LangGraph (tool-using agents, multi-step orchestration, parallel multi-agent patterns); integrate LLM pipelines with knowledge graphs (Neo4j) for structured reasoning over audit and compliance data; implement human-in-the-loop checkpoints, auditability controls, and enterprise governance guardrails.
• Evaluate and integrate frontier LLMs (Gemini 2.5 Pro/Flash, Claude, GPT-4o) and specialized models; define LLM selection criteria, cost/latency tradeoffs, and quality benchmarks; run prompt iteration cycles and structured output evaluation to meet acceptance criteria across audit-specific use cases.
• Own API and integration service design using FastAPI and Express; deliver scalable RESTful interfaces and streaming endpoints (Server-Sent Events); coordinate integration with downstream/upstream enterprise systems, Microsoft Azure AD identity and access management (IAM), and AI task monitoring pipelines.
• Design and deliver data engineering pipelines to curate governed datasets for GenAI solutions-including document parsing, structured extraction, and embedding preparation; partner with data governance and risk teams on lineage, access controls, and data quality standards for AI model inputs.
• Operationalize GenAI application deployments using containerized patterns (Docker, Kubernetes, Helm); implement monitoring and observability for AI workloads (performance, cost, model drift, output quality signals) and drive continuous improvement through incident learnings and release management.
• Advise on emerging GenAI models, frameworks, and toolkits (e.g., Gemini 2.5, Claude, LangGraph, Milvus, Neo4j); prototype and recommend options with explicit tradeoffs across audit value, delivery effort, risk, compliance, and total cost of ownership (TCO); guide responsible AI adoption within regulated environments.

       Collaborate with cross-functional teams (product, engineering, data, risk, and stakeholders) to deliver adoption-ready solutions and documentation.

The team
Our team culture is collaborative and encourages team members to take initiative and seek on-the-job learning opportunities. Audit & Assurance services are focused on engagements related to independent External Audit services, Accounting, Controls & Reporting Advisory, and Specialized Assurance & Sustainability. We bring together the diverse skills and industry experience of our people, leading-edge technology, and a global network to deliver high-quality audits of financial statements and internal controls over financial reporting, along with assurance reports and valuable advice and insights across the corporate reporting landscape. Learn more about Deloitte Audit & Assurance.  

Qualifications
Required:

       Bachelor's degree (or equivalent) in Computer Science, Engineering, Data Science, or a related field (advanced degree a plus).

       4+ years of experience in software engineering, full stack development, and/or AI/ML solution delivery.

       Python programming (production-grade) and strong SQL.

       Natural Language Processing (NLP) applied to GenAI solutions.

       Agentic AI design/implementation, including LangChain, LangGraph, and LlamaIndex.

       Hands-on experience with RAG architectures and implementation.

       Strong prompt engineering (design, iteration, and evaluation).

       Experience with vector databases (e.g., Milvus, Pinecone, Chroma, FAISS or similar) and embedding-based retrieval.

       Experience with GenAI model build: training, fine-tuning, and validation; practical LLM evaluation using common metrics.

       Experience with model deployment (serving, monitoring, iteration) and production hardening.

       Experience with containers (e.g., Docker) and scalable runtime patterns.

       Experience building ETL pipelines and data engineering solutions (data quality, preprocessing, and curation).

       API development and integration (RESTful services); backend development using FastAPI (or equivalent).

       Experience integrating multiple LLM provider APIs (OpenAI, Anthropic, Google GenAI/Gemini) using their respective Python SDKs; ability to swap and benchmark models across providers.

       Experience with asynchronous messaging and real-time data patterns (Redis pub/sub, Server-Sent Events, WebSockets) for AI task orchestration and streaming output delivery.

       Experience with cloud AI/ML services with a focus on GCP (Vertex AI, GKE, Cloud Storage, Filestore); familiarity with Azure and AWS AI/ML services a plus.

       You should reside within a commutable distance of your assigned office with the ability to commute daily, if required

       You can expect to co-locate on average 3 times a week with variations based on types of work/projects and clien...