AI Engineer

Join our team and contribute to the development of cutting-edge, AI-driven applications designed to revolutionize data interaction. We are seeking a proactive AI Engineer with 2-3 years of experience, passionate about working with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and conversational AI systems. This role involves hands-on development, integration, and refinement of AI-powered solutions within a dynamic, collaborative setting.

Responsibilities

• Design and construct AI-powered applications and conversational agents leveraging LLMs for interaction with structured data sources such as SQL databases and Snowflake.
• Develop and integrate RAG pipelines utilizing vector databases like Pinecone, FAISS, ChromaDB, or similar technologies.
• Build sophisticated conversational workflows using AI orchestration frameworks such as LangChain, LlamaIndex, or equivalent libraries.
• Implement natural language-to-SQL or data-querying capabilities under the guidance of senior engineering professionals.
• Integrate AI applications with external tools, APIs, and data sources; prior exposure to agent frameworks or tool-based AI patterns is advantageous.
• Collaborate effectively with data engineers, product managers, and business stakeholders to translate requirements into functional AI prototypes and features.
• Support the deployment, monitoring, and optimization of AI applications, adhering to established engineering and MLOps practices.
• Assist in the testing, evaluation, and iteration of AI models and workflows to enhance accuracy, relevance, and user experience.
• Stay abreast of the latest advancements in Generative AI tools, models, and best practices, applying this knowledge to real-world use cases.

Required Qualifications

• 3-5 years of practical experience in AI/ML, software engineering, or applied Generative AI development.
• Proficient Python programming skills, including experience in building APIs or backend services.
• Hands-on experience working with LLMs and Generative AI APIs (e.g., OpenAI, Azure OpenAI, Anthropic, Hugging Face).
• Practical experience or demonstrable understanding of RAG concepts, embeddings, and vector databases.
• Experience working with structured databases (e.g., Postgres, MySQL, Snowflake) and proficiency in writing SQL queries.
• Familiarity with modern software development methodologies, including Git, code reviews, and basic CI/CD principles.
• Strong analytical and problem-solving abilities, with a commitment to continuous learning in a fast-paced environment.

Nice To Have

• Exposure to AI orchestration or agent frameworks (e.g., LangChain, LlamaIndex, CrewAI).
• Basic understanding of MLOps concepts (e.g., Docker, CI/CD, MLflow, model versioning).
• Experience deploying applications on cloud platforms like AWS, Azure, or GCP.
• Previous involvement in projects related to chatbots, virtual assistants, or intelligent automation solutions.
• Familiarity with BI or analytics tools (e.g., Power BI, Tableau) for the downstream utilization of AI outputs.

Benefits

Health Insurance, Accident Insurance. Salary will be determined based on various factors including location, education, qualifications, experience, technical skills, and business requirements.

Additional Responsibilities

• Actively participate in OP's monthly team meetings and contribute to team-building initiatives.
• Engage in OP's technical discussions and peer review processes.
• Contribute content and collaborate through the OP-Wiki/Knowledge Base.
• Provide timely status reports to OP Account Management as required.