Lead AI Engineer
About The Position
The Lead AI Engineer designs, develops, and deploys scalable generative AI and conversational AI solutions for enterprise environments. The role leads implementation of LLM-powered applications, RAG architectures, multi-agent workflows, and AI-driven APIs, with attention to security, reliability, and performance. The engineer works with product, engineering, and business stakeholders to advance AI adoption and deliver measurable business value. The position is based at a client site in Dallas, Texas, for 2–3 days per week. The role also involves evaluating and optimizing AI solutions and establishing monitoring and evaluation practices for production systems.
Requirements
- At least 3 years of experience in AI/ML engineering, software engineering, or solution architecture, including at least 1 year focused on generative AI, LLMs, or conversational AI.
- Strong hands-on experience with Python, FastAPI, Google Cloud Platform (GCP), and Google ADK.
- Experience designing and implementing enterprise chatbots and agentic AI solutions.
- Deep expertise in RAG architectures, knowledge bases, embeddings, and vector databases.
- Strong understanding of retrieval techniques, including hybrid search, semantic search, and BM25.
- Experience building multi-agent and agent-orchestration workflows using frameworks such as Google ADK, LangGraph, Copilot Studio, or similar.
- Knowledge of AI evaluation methodologies, including techniques for measuring accuracy, grounding, hallucination rates, and response quality.
- Familiarity with API design, integration patterns, observability, resiliency mechanisms, and circuit-breaker patterns.
- Experience with prompt engineering and meta prompting.
- Experience with approaches to fine-tuning or reinforcement learning.
- Understanding of agent memory usage.
- Experience with vector databases.
- Excellent communication and collaboration skills, with the ability to work across engineering, product, and business teams.
Nice To Haves
- Experience in healthcare, patient engagement, or regulated industry environments.
- Experience with production monitoring and continuous improvement of conversational AI systems using real-world interaction data.
Responsibilities
- Design, develop, and deploy scalable generative AI and chatbot solutions for production environments, ensuring security, performance, and reliability.
- Build Python-based APIs and agentic workflows using Google ADK, FastAPI, LangGraph, Copilot Studio, or similar frameworks.
- Implement and optimize RAG architectures, vector databases, and knowledge retrieval systems to improve chatbot accuracy and reduce hallucinations.
- Develop and maintain backend services that expose AI capabilities through secure, scalable APIs.
- Design agentic AI patterns, including supervisor/orchestrator, fan-in/fan-out, retrieval, research, and evaluation workflows.
- Establish observability, monitoring, and evaluation frameworks to measure chatbot performance, response quality, and business outcomes.
- Evaluate emerging AI models, tools, and platforms and recommend best practices for enterprise adoption.
- Collaborate with product, engineering, and business stakeholders in a spec-driven development environment.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
