• 
  It is a 100% Onsite position in Dallas, TX.
• 
  Local Candidates preffered.

• 
  Focus on building AI-driven solutions using Python, including LLMs, embeddings, knowledge graphs, and RAG architectures..
• 
  Eligible Hacker Rank assessment.

• 
  Build GenAI applications leveraging foundation models and advanced architectures such as GraphRAG.
• 
  Develop autonomous AI agents using modern agentic frameworks.
• 
  Design and deploy RAG and GenAI services using Python (FastAPI), Docker, and cloud platforms (AWS, Azure, or GCP).
• 
  Build scalable REST APIs that power LLM-driven applications integrated with enterprise data sources.
• 
  Implement LLM evaluation frameworks using tools such as Ragas, LangSmith, or custom benchmarks to measure answer relevance, groundedness, and hallucination rates.
• 
  Apply LLMOps/MLOps practices, including CI/CD pipelines, prompt/version management, automated testing, and monitoring of latency, cost, and response quality.
• 
  Develop systems leveraging embeddings at scale, knowledge graphs, and ontology extraction.
• 
  Collaborate across engineering teams, mentor developers, and help drive innovation in GraphRAG and agentic AI architectures.

Requirements

• 
  Degree in Computer Science, AI/ML, or related field.
• 
  5+ years of AI/ML-focused software engineering experience.
• 
  Production experience building LLM-based or agentic AI systems.
• 
  Strong expertise in Python and modern AI frameworks.
• 
  Experience with embeddings, knowledge graphs, ontology extraction, and advanced RAG/GraphRAG implementations.
• 
  Full-stack development experience (Python back end + modern front end).
• 
  Experience deploying AI workloads to AWS, Azure, or GCP.
• 
  Familiarity with LLMOps/MLOps tooling and model evaluation frameworks.
• 
  Strong problem-solving, communication, and collaboration skills.