Artificial Intelligence Engineer - Gen AI / LLM Developer

Ojas Softech is seeking a skilled Gen AI Developer / LLM Engineer with over 2 years of practical experience in creating, deploying, and scaling advanced AI applications powered by Large Language Models (LLMs). This role is ideal for a candidate with robust backend development capabilities, proven experience with Agentic AI frameworks, and a strong drive to build impactful real-world Generative AI solutions.

We are actively hiring for this position in Noida.

About the Role

We are looking for a Gen AI Developer / LLM Engineer with 2+ years of hands-on experience in building, deploying, and scaling AI applications using Large Language Models (LLMs). The ideal candidate should have strong backend skills, experience with Agentic AI frameworks, and a passion for building real-world GenAI solutions.

Key Responsibilities

• Design, develop, and deploy GenAI applications utilizing LLMs such as OpenAI, Anthropic, and various open-source models.
• Construct and refine LLM pipelines employing LangChain or similar frameworks.
• Implement Agent / Agentic AI workflows designed for autonomous task execution.
• Integrate vector databases to enable efficient semantic search and Retrieval Augmented Generation (RAG).
• Develop scalable backend APIs using FastAPI.
• Containerize applications effectively using Docker and manage their deployments.
• Leverage a Linux environment for both development and deployment processes.
• Optimize prompts, embeddings, and inference performance for enhanced efficiency.
• Collaborate closely with product, data, and engineering teams to translate complex business requirements into practical AI solutions.
• Ensure the security, scalability, and optimal performance of all GenAI systems.

Required Skills

• Minimum 2 years of experience in software development or AI/ML roles.
• Exceptional proficiency in Python programming.
• Demonstrated hands-on experience with LLMs and GenAI frameworks.
• Practical knowledge and application of LangChain.
• Proven experience working with various Vector Databases including Pinecone, FAISS, Weaviate, Chroma, and others.
• Experience in building robust APIs using FastAPI.
• Familiarity with Docker for containerized deployments.
• Solid understanding of Linux systems and their operational aspects.
• Knowledge of Agent-based or Agentic AI systems.

Good to Have (Preferred Qualifications)

• Prior experience with RAG pipelines and advanced prompt engineering techniques.
• Exposure to major cloud platforms such as AWS, GCP, or Azure.
• Familiarity with popular open-source LLMs like LLaMA, Mistral, etc.
• Experience in the production deployment of GenAI models.
• Understanding of Continuous Integration/Continuous Deployment (CI/CD) pipelines.

What We Offer

• A unique opportunity to work on groundbreaking GenAI projects.
• A high-ownership and learning-centric work environment.
• Competitive salary, commensurate with experience.
• A collaborative and growth-driven company culture.