We are seeking a skilled Custom Software Engineer to design, code, and enhance components across various systems and applications. This role involves leveraging modern frameworks and agile methodologies to deliver scalable, high-performing custom software solutions tailored to specific business requirements.

Key responsibilities include developing and optimizing AI-powered applications, building enterprise GenAI solutions, and creating intelligent search and Agentic AI workflows. The ideal candidate will have a strong background in Python development and experience with LLMs, RAG, and vector databases.

Develop and maintain AI-powered applications using Python, focusing on enterprise GenAI solutions with LLMs and Natural Language Interfaces.

Build and refine RAG, Text-to-SQL, Semantic Search, and Agentic AI solutions. Design and implement efficient data ingestion and processing pipelines.

Integrate AI models with existing enterprise applications and APIs, ensuring smooth communication and functionality. Monitor, troubleshoot, and optimize AI application performance for peak efficiency.

Contribute to key architecture decisions and provide mentorship to team members, fostering a collaborative development environment.

A minimum of 2-5 years of professional experience is required, with a strong emphasis on Python development (4+ years) and AI/GenAI/RAG application development (2+ years).

Proficiency in core Python, OOPs, Design Patterns, and Unit Testing is essential. Experience with web frameworks like FastAPI, Flask, or Django REST Framework is highly desirable.

Solid understanding of SQL, Data Modeling, and Shell Scripting. Familiarity with data manipulation libraries such as Pandas and NumPy is expected.

Knowledge of Authentication & Authorization mechanisms (JWT, OAuth, SSO) is required. Experience integrating with LLMs (OpenAI, Gemini, Anthropic) and utilizing Vector Search, Semantic Search, and Agentic AI Workflows is crucial.

Candidates must demonstrate experience with GenAI Tooling, Natural Language Interfaces, RAG Pipeline Development, Text-to-SQL Systems, and working with libraries like LangChain and Hugging Face Transformers. Familiarity with Embedding Models and Vector Databases (FAISS, Qdrant, Weaviate) is necessary for creating and managing embeddings and vector stores.