GenAI Engineer

Aubrant Digital LLC; United States; Hybrid; USD 150,000 - 210,000; Full time

Job summary

Aubrant Digital LLC is seeking an experienced Generative AI Engineer to support enterprise AI enablement initiatives. This role focuses on GenAI workflows, automating processes across platforms like AWS, Microsoft 365, and other GenAI libraries.

The ideal candidate has 10+ years in software engineering, 2–3 years in Generative AI, and strong Python skills, with hands-on work in MCP, A2A, and RAG architectures to scale our AI CoE.

Qualifications

• Over 10 years of software engineering experience, including 2–3 years dedicated to Generative AI and RAG architecture.
• Over 3 years of cloud-native experience, preferably on AWS.
• Over 5 years of hands-on Python experience.
• Experience building interoperable AI agents using MCP and Google A2A.

Responsibilities

• Design GenAI solutions using prompt engineering, RAG, and custom pipelines.
• Create interoperable AI agents using MCP and Google A2A.
• Automate parsing of unstructured content into structured data.
• Build enterprise-wide reusable services and components.
• Develop MCP hosts, clients and servers.
• Establish frameworks for automated LLM testing and regression suites.
• Integrate with internal/external web services with secure auth.
• Advocate for enterprise security and AI governance.

Skills

Python

LLM APIs

Prompt engineering

RAG architecture

MCP

Google A2A

REST APIs

AWS

LangSmith

Tools

AWS

LangSmith

CloudWatch

Bedrock

Step Functions

API Gateway

IAM

Google A2A

Job description

About Aubrant

Aubrant Digital is a leader in multi‑shore custom application development. We are passionate about solving our clients’ business problems through consultative teamwork, innovative software, and proven processes. We’ve served more than 50 clients and delivered hundreds of high quality, custom enterprise applications. Our clients value us as integral team members who get the job done on time and on spec, and we are proud of our high client retention rate and under 2% staff turnover. With offices in New Jersey, Boston, Costa Rica, and Eastern Europe, we execute the full software lifecycle, from architecture and design through development, QA and application maintenance & support. Our company culture emphasizes client service, trust‑based relationships, and innovation.

Overview:

We’re seeking an experienced strong Generative AI Engineer to support enterprise‑wide AI enablement initiatives. This role will focus on building robust GenAI and agentic AI workflows, automating workflows and working across diverse platforms like AWS, Microsoft 365, MS Copilot, and other 3rd party GenAI platforms and libraries.

The ideal candidate is highly self‑driven and comfortable operating across architecture, and hands‑on implementation. This is a high‑impact role supporting an AI Center of Excellence (CoE) at scale.

Experience:

• Over 10 years of robust software engineering experience, including 2 to 3 years of dedicated hands‑on work in Generative AI and Retrieval‑Augmented Generation (RAG) architecture
• Over 3 years of cloud native experience preferably on AWS.
• Over 5 years of hands‑on experience with Python
• Experience building interoperable Agentic AI Proof of Concepts using Model Context Protocol (MCP) and/or Google A2A.

Key Responsibilities:

• Design and develop GenAI solutions using prompt engineering, Retrieval‑Augmented Generation (RAG), and custom pipelines
• Design and develop interoperable AI agents using Model Context Protocol (MCP) and Google A2A
• Automate workflows involving parsing unstructured content such as emails, documents, and web pages in to highly accurate and reliable structured content
• Automate building documents using data and content from various diverse sources
• Build enterprise‑wide reusable services and components
• Design and build MCP hosts, clients and servers
• Establish frameworks for automated LLM testing
• Create regression test suites to detect drift or prompt breakage
• Integrate with internal and external web services using secure authentication and authorization mechanisms
• Adopt and ensure safe practices to protect against prompt injections, jailbreaks, and conform to enterprise security guidelines
• Experience with agile methodologies and ability to independently document user stories in the absence of Business Analyst
• Collaborate with the AI CoE team to ensure scalability, reusability, and alignment with governance standards

Required Skills:

• Very strong Python skills.
• Strong hands‑on experience with LLM APIs (OpenAI, Azure OpenAI, Gemini, Anthropic, etc.) using Python and Python based frameworks
• Strong hands‑on experience in prompt engineering, context construction, grounding strategies
• Strong hands‑on experience with Retrieval Augmented Generation (RAG) extracting, chunking and create embeddings from unstructured documents from diverse sources including O365(email, word, excel), PDFs, and webpages.
• Comfortable building Model Context Protocol (MCP) clients, servers and hosts.
• Strong Expertise in building REST APIs and integrating with internal/external APIs
• Hands‑on experience with Intelligent Document Processing and/or OCR technologies on complex documents
• Knowledge of Google A2A
• Deep experience in AWS (Lambda, Bedrock, Step Functions, API Gateway, IAM)
• Strong experience with monitoring using LangSmith, CloudWatch, or other similar GenAI observability tools
• Excellent GenAI foundations and concepts
• Clear understanding of enterprise data privacy, AI governance, and observability

Nice to Have:

• Experience with Microsoft Copilot extensibility (Graph connectors, plugins, or adaptive cards)
• Ability to build and orchestrate AI‑to‑AI interactions using Google A2A, integrating multiple agents or tools
• Strong traditional ML Experience

Success Profile:

• You’re a builder who can translate fuzzy business needs into elegant GenAI and Agentic AI workflows
• You’re a problem solver who’s comfortable navigating across cloud platforms, tools, and data sources
• You’re collaborative, with the ability to work independently while aligning with enterprise AI goals