GenAl Engineer (Google ADK + Agentic AI)

Hi,
Hope you are doing well.

I have an urgent opening for GenAl Engineer (Google ADK + Agentic AI) position. Kindly review the job description below and if interested, share your most recent resume in word format.


**Kindly share your updated resume**


Job Title: GenAl Engineer (Google ADK + Agentic AI)
Location: Charlotte, NC (Onsite) – Locals Only
Job Type: Contract – W2


Note- In-person interview required for this role.

Job Description:
We are seeking a Lead Al Engineer to design, build, and scale Agentic and Generative Al solutions that deliver measurable business outcomes. This role is hands-on and includes leading moderately complex initiatives, contributing to large-scale technical strategy, and serving as a technical escalation point while mentoring engineers.

Skills: LLM Basics, RAG Pipeline, Transformers and Chatbots - Python programming, Langchain and Lang graph frameworks - MLOps, Measuring success criteria

• Develop agents with Google ADK, leveraging its multi-agent architecture, flexible orchestration, tool ecosystem (including MCP tools), built-in evaluation, and deployment-ready patterns.
• Lead or contribute to moderately complex initiatives and deliverables within Al/ML and software engineering domain environments, with accountability for high-quality outcomes.
• Contribute to large-scale planning of strategies for generative Al capabilities, including platform patterns, engineering standards, and operational readiness.
• Design, code, test, debug, and document Al-enabled services and applications, including upgrades and deployments across environments.
• Design and develop Generative Al applications using large language models (LLMs), retrieval-augmented generation (RAG), and agentic frameworks; integrate Al capabilities into existing enterprise products and systems.
• Build production-grade agentic solution using LanChain and LangGraph combining rapid composition with explicit state-machine orchestration
• Engineer secure tool execution patterns (service-to-service calls, least privilege, auditability) and align with enterprise approaches to agent-to-agent communication (A2A) and MCP-based tool integration where applicable.
• Evaluate moderately complex technical challenges requiring in-depth assessment of Al technologies, orchestration approaches, model behavior, and enterprise integration patterns.
• Troubleshoot and resolve complex technical issues across Al services and models; ensure monitoring and operational hygiene to improve efficiency and mitigate risk.
• Lead, design, develop, test, and implement application components, tools, utilities, and analytics related to Al lifecycle needs (e.g., evaluation, quality monitoring, model drift monitoring).
• Collaborate and consult with peers, colleagues, and mid-level managers to resolve technical challenges and achieve goals.
• Act as an escalation point, providing guidance and direction to less experienced staff; drive engineering excellence across the team.
• Ensure delivery aligns with policies, procedures, compliance requirements, and risk management expectations for supported areas.

Desired Qualifications:

• Strong hands-on engineering in Java and/or Python, with experience building production services and integrating Al components into enterprise applications.
• Experience in building and operating vector databases to enable semantic retrieval, embedding-based search, and Al-driven knowledge systems.
• Experience with vector search / retrieval patterns and grounding approaches used for enterprise RAG solutions.
• Experience implementing safe controls such as human-in-the-loop approvals, exception escalation, and policy guardrails for agentic systems.
• Experience with cloud environments (e.g., Azure, AWS, Google Cloud) and managing applications in cloud/container ecosystems.
• Experience with CI/CD and automated deployments and "test-centric" engineering methodologies (TDD/BDD).
• Familiarity with event streaming or messaging technologies (e.g., Kafka).
• Strong analytical/problem-solving skills and ability to explain model behaviors, failure modes, and technical tradeoffs to stakeholders.
• Familiarity with financial services technologies and regulated environments is a plus.