Generative AI Software Engineer

Job Title: Generative AI Software Engineer

Location: Dallas, TX (Preferred) | Atlanta, GA (Optional)

Experience: 3–5 years

About IVoyant:

At IVoyant, we are building intelligent, adaptive systems that push the boundaries of automation, decision-making, and user experience. We are looking for a Generative AI Software Engineer who thrives in applying large language models (LLMs), building agentic AI systems, and deploying them through robust APIs and microservices.

What You’ll Do:

• Build and operationalize Generative AI and Agentic AI applications using Python.
• Design and deploy LLM-powered APIs and microservices that scale in real-world environments.
• Architect autonomous agents with capabilities like memory, reasoning, planning, and tool integration.
• Implement RAG (Retrieval-Augmented Generation), prompt chaining, and LLM orchestration frameworks (e.g., Lang Chain, Llama Index).
• Work closely with data teams to understand, prepare, and leverage structured and unstructured data for model use.
• Optimize performance, reliability, and cost of Gen AI services in production.
• Write clean, testable Python code and collaborate cross-functionally across product, engineering, and DevOps teams.

What You Bring:

• 3–5 years of professional software development experience, primarily using Python.
• Hands-on experience with LLMs (e.g., OpenAI, Anthropic, Mistral, Llama) and agent frameworks (AutoGPT, Crew AI, etc.).
• Strong understanding of building RESTful APIs and microservices to expose Gen AI features.
• Proficiency with cloud deployment (Azure, AWS, or GCP) and containerization (Docker, Kubernetes).
• Experience working with data pipelines, embeddings, vector databases (e.g., FAISS, we aviate, Pinecone).
• Familiarity with orchestration frameworks (Lang Chain, Llama Index) and Gen AI tooling.
• Ability to translate AI research into usable product features.

Nice to Have:

• Experience with fine-tuning models or using open-weight models.
• Exposure to multi-modal models (text, image, video).
• Contributions to open-source AI/ML projects.
• MLOps or CI/CD experience for ML workflows.