Senior AI Engineer

VDart, Inc. Logo
VDart, Inc.
Atlanta, GA, United States
  • Construction
  • Applications have closed

Job Title: AI Engineer

Location:Dallas, TX / Atlanta, GA

Duration: / Term:6 months

Job Description:

Experience Desired: 8 Years.

Key required skills

The candidate should be able to serve as the lead technical contributor for designing and deploying enterprise-grade AI systems. This role demands a senior AI engineer who can handle high-level architectural design and hands-on implementation of complex agentic workflows. The candidate will be responsible for building the “AIObserve” ecosystem, ensuring that probabilistic AI outputs are translated into deterministic, secure, and high-value business outcomes.

Core Responsibilities

  • Architecting Agentic Systems: Design and implement multi-agent systems using the Model Context Protocol (MCP) to enable seamless tool-calling across platforms like Atlassian and GitHub.
  • Enterprise RAG Implementation: Lead the development of sophisticated Retrieval-Augmented Generation (RAG) layers, integrating vector databases like Milvus with enterprise knowledge bases (Jira/Confluence).
  • Orchestration & Workflow Automation: Build and optimize backend services using FastAPI and Azure Bot Service to handle real-time message routing and automated ticket fulfillment.
  • High-Privilege Automation: Develop secure browser automation scripts using Python and Playwright to handle complex tasks such as RBAC validation and post-true-up process automation.
  • Security & RBAC Engineering: Engineer robust Role-Based Access Control (RBAC) within AI agents to ensure high-privilege operations are executed safely and within compliance.
  • Performance Tuning: Optimize system latency to ensure AI responses and backend acknowledgments meet strict enterprise thresholds (< 7 seconds).
  • Architecting Observability Pipelines: Design and implement end-to-end telemetry for AI agents. This includes capturing not just system logs, but also LLM-specific traces (latency, token usage, and “hallucination” scores) to provide a 360-degree view of system health
  • LLMOps Infrastructure: Own the deployment lifecycle, including CI/CD for prompt engineering, automated testing of RAG retrieval accuracy, and monitoring for “model drift” in production.
  • Cross-functional Collaboration: Working with product managers, data scientists, and business stakeholders to translate needs into AI solutions.

Preferred Qualifications:

  • 7 years of experience in applied AI engineering or related role with 2 years in agentic development, and/or with a combination of context/prompt engineering
  • Expert-level Python proficiency with emphasis on modular, object-oriented code, strict typing, and rigorous unit/integration testing for production
  • Experience with building both conversational agents and workflow agentic processes in production
  • Applied experience with multiple LLM stacks/frameworks (e.g., OpenAI, Claude, Gemini, RAG pipelines), and agent orchestration systems (e.g., LangGraph, AutoGen, CrewAI, or LangChain building collaborative autonomous and complex AI workflows
  • Demonstrated comfort with prompt design strategies (chain-of-thought, few-shot) and context window optimization to ensure high-quality LLM outputs
  • Familiarity with cloud platforms (AWS/Azure), REST APIs, and containerization (Docker, K8s)
  • Experience implementing and managing Vector Databases (e.g., Pinecone, Milvus, Weaviate) for RAG (Retrieval-Augmented Generation) pipelines.
  • Experience with Azure bot services, Fast API, OAuth for API security is recommended.
  • Proficiency in Databricks and SQL (DDL/DML) driving scalable data architecture and holistically integrating prompt designs, vector databases, and memory strategies to deliver advanced LLM solutions
  • Experience developing and applying state-of-the-art techniques for optimizing training and inference software to improve hardware utilization, latency, throughput, and cost
  • Passion for staying abreast of the latest AI research and AI systems, and judiciously applying novel techniques in production
  • Excellent communication and presentation skills, with the ability to articulate complex AI concepts to peers

Key Skills:

AI Engineering, Prompt Engineering, Python, RAG

Apply for job