Join us as a Custom Software Engineer to craft innovative software solutions. You will design, code, and enhance system components, utilizing modern frameworks and agile methodologies to deliver scalable and high-performing applications tailored to specific business needs. This role emphasizes building custom software that directly addresses unique organizational challenges.

Design, develop, and maintain AI-powered applications using Python. Build enterprise GenAI solutions leveraging LLMs and Natural Language Interfaces. Develop and optimize RAG, Text-to-SQL, Semantic Search, and Agentic AI solutions. Implement scalable data ingestion and processing pipelines. Integrate AI models with enterprise applications and APIs. Monitor, troubleshoot, and optimize AI application performance. Contribute to architecture decisions and mentor team members.

We are seeking an experienced Python + AI-GenAI Engineer proficient in creating enterprise-grade GenAI applications, intelligent search solutions, Agentic AI workflows, and scalable data processing pipelines. A strong background in LLMs, RAG, Vector Databases, and modern AI frameworks is essential. Candidates should possess at least 2-5 years of relevant experience, with a minimum of 4+ years in Python development and 2+ years in AI-GenAI-RAG and LLM application development. A foundational understanding of Object-Oriented Programming, Design Patterns, and Unit Testing is required, alongside experience with web frameworks like FastAPI, Flask, or Django. Proficiency in SQL, data modeling, and shell scripting is also key. Experience with libraries such as Pandas and NumPy, along with robust authentication and authorization mechanisms, is expected. Familiarity with LLM integrations (OpenAI, Gemini, Anthropic), vector search technologies, and GenAI tooling is crucial. Experience in RAG pipeline development, Text-to-SQL systems, and AI frameworks like LangChain, LangGraph, and Hugging Face Transformers is highly valued. Knowledge of embedding models and vector databases (FAISS, Qdrant, Weaviate) is necessary for creating and managing embeddings and vector stores. Experience with Grafana monitoring and Git, including CI/CD practices, is also required. Familiarity with cloud platforms like Azure OpenAI, AWS Bedrock, and containerization technologies such as Docker and Kubernetes is beneficial.