Job Title: AI Engineer
Location: Charlotte, NC (Hybrid)
Type: : Long Term Contract
Job Summary:
we are seeking a highly motivated and experienced GenAI engineer to join our team and play a critical role in designing developing and deploying innovative generative AI solutions. You will be responsible for the entire life cycle of jenai projects from prototyping and experimentation to building evaluating and deploying production ready applications. You will leverage your expertise in large language models(LLM), prompt engineering RAG pipelines , and AI agents to solve complex business problems and drive significant value for the organization especially in the areas of incident summaries batch recovery and change assessments. A key aspect of this role is the ability to build full-fledged prototypes including a user interface to demonstrate the potential of GenAI Solutions.
Key responsibilities:
Prompt engineering and optimization: Design and refine advanced prompt templates for high performing janai outputs across varied use cases such as incident summaries, batch recovery and change assessments. Focus on achieving measurable improvements in accuracy efficiency and user satisfaction.
RAG pipeline development: develop and implement retrieval augmented generation (RAG) pipelines using tools like Lang chain llama index semantic search techniques and vector databases (e.g. Elasticsearch, Weaviate, Pinecone, Chroma). Optimize RAG pipelines for performance scalability data relevance and cost effectiveness.
AI agent development and orchestration: build and orchestrate modular AI agents capable of reasoning across multiple steps and acting within internal workflows (e.g., service now, confluence, jira, Ms. Teams). Implement agentic workflows for tasks such as automated problem resolution knowledge discovery and process automation. Experience with agent space or similar agentic frameworks is highly desirable.
Collaboration and integration: partner with SRE dev SEC OPS and observability teams to translate operational data into structured GenAI insights. Integrate genai solutions with enterprise systems and data sources ensuring seamless data flow and interoperability.
Prototyping and platform exploration: experiment with jenai platforms like Microsoft Copilot Studio Azure open AI and Google's AI platform including vertex AI to identify optimal solutions for specific business challenges related to incidents summaries batch recovery and change assessments. Develop proof of concept applications focusing on secure API integration and intuitive user interfaces. Thoroughly document their prototyping process including successes failures key learnings to contribute to a culture of continuous improvement and knowledge sharing within the team. Explore integration with existing Microsoft platforms.
Guardrails & Evaluation: Establish guardrails, prompt evaluation metrics, and test cases for output safety, bias mitigation, and hallucination control. Implement robust monitoring and alerting
systems to ensure the reliability and trustworthiness of GenAl solutions.
Governance & Compliance: Collaborate with the enterprise GenAl Review Board and contribute to alignment with firmwide architecture standards, security policies, and ethical guidelines.
UI/UX Development: Develop user-friendly interfaces for GenAl prototypes using a front-end language such as Angular or React.js.
Required Qualifications:
- 3+ years of experience in LLM application development, including prompt design, RAG pipelines, or agentic Al systems.
- Strong understanding of OpenAl, Gemini, or open-source models (e.g., LLAMA 3, Mistral) and their integration patterns. Must be able to articulate the strengths and weaknesses of different models and select the appropriate model for a given task.
- Proficient in Python, with experience using GenAl tooling (e.g., Lang Chain, LangGraph, lamaindex, Hugging Face, MCP, ADK, AZA).
- Experience with Model Evaluation frameworks like Ragas, Truelens and methods for Explainability tracking like SHAP, LIME.
- Experience with Gen Al cost optimization.
- Experience deploying models via secure APIs in regulated environments, ideally within financial services.
- Demonstrated ability to integrate GenAl tools with enterprise systems (ServiceNow, Jira, Confluence, MS Teams).
- Deep understanding of prompt engineering, prompt chaining, system prompts, and contextual grounding techniques.
- Experience with at least one front-end UI/UX language (e.g., Angular, React.js) to build functional prototypes.
- Strong problem-solving skills and the ability to work independently and as part of a team.
- Excellent communication and presentation skills.
Your sincerely,
Ajay Sharma | Sr. Technical Recruiter.
Net2Source Inc.
Fax: (201) 221-8131 | Email: ajays@net2source.com
Global HQ Address: 270 Davidson Ave, Suite 704, Somerset, NJ 08873, USA