LLM Developer

About the Role

We are looking for a motivated and hands-on LLM Engineer with 1–2 years of experience in software development, AI/ML, or Generative AI. In this role, you will help design, develop, and deploy AI-powered applications using Large Language Models (LLMs) based at our office in Ahmedabad, India.

The ideal candidate should have practical experience with LLM APIs, Python, Retrieval-Augmented Generation (RAG), prompt engineering, embeddings, and AI application development. You should enjoy experimenting with emerging AI technologies and have the ability to transform prototypes into reliable, scalable, and production-ready solutions.

Key Responsibilities

• Design, develop, and integrate LLM-powered features into existing and new applications tailored for local markets like Gujarat.
• Work with LLM APIs and platforms such as OpenAI, Google Gemini, Anthropic, and open-source models to build India-centric solutions.
• Build and optimize Retrieval-Augmented Generation (RAG) pipelines for knowledge-based AI applications serving regional clients.
• Implement embeddings, vector databases, semantic search, and document retrieval systems with an eye on cost efficiency relevant to the Indian market.
• Design, test, and refine prompts to improve response accuracy, consistency, and relevance for diverse use cases.
• Implement function calling, structured outputs, and AI-driven workflows to enhance operational capabilities.
• Develop REST APIs and backend services using Python, adhering to industry best practices.
• Evaluate LLM outputs and troubleshoot hallucinations, retrieval issues, and inconsistent responses in real-world scenarios.
• Optimize AI applications for performance, latency, scalability, and cost efficiency within the constraints of local infrastructure.
• Collaborate with engineering and product teams to integrate AI capabilities into production systems deployed locally or via cloud providers available globally.
• Stay up to date with the latest LLM models, frameworks, tools, and Generative AI developments by engaging with the global community while applying knowledge here in Ahmedabad.

Required Skills and Qualifications

• 1–2 years of experience in software development, AI/ML, or Generative AI within a professional setting (not just academic).
• Strong programming skills in Python to build robust applications.
• Hands-on experience with at least one LLM platform, such as OpenAI, Google Gemini, Anthropic, or open-source LLMs like those running on cloud platforms accessible from India.
• Good understanding of prompt engineering and LLM application development for practical business problems.
• Practical knowledge of RAG architecture and retrieval pipelines to create intelligent search experiences.
• Familiarity with embeddings, vector databases, and semantic search technologies that are cost-effective and scalable.
• Basic understanding of REST APIs and backend development using modern frameworks.
• Working knowledge of Git and GitHub for version control in a distributed team environment.
• Strong analytical, problem-solving, and debugging skills to navigate complex AI challenges.
• Ability to learn new technologies quickly and work independently on small AI projects relevant to the industry.

Good to Have

• Experience with LLM frameworks such as LangChain, LlamaIndex, or LangGraph for rapid prototyping.
• Familiarity with vector databases such as Pinecone, Qdrant, Weaviate, Chroma, or pgvector hosted on cloud infrastructure.
• Experience developing APIs using FastAPI or Flask to serve high-throughput endpoints.
• Basic knowledge of databases such as PostgreSQL or MongoDB for structured data handling.
• Familiarity with Docker and application containerization for seamless deployment across environments.
• Exposure to deploying applications on AWS, Microsoft Azure, or Google Cloud Platform (GCP), which offer significant benefits in the region.
• Understanding of LLM evaluation, monitoring, and observability tools like LangSmith or Arize AI.
• Experience with AI agents, tool calling, and multi-step AI workflows for automation tasks.
• Familiarity with testing, debugging, and improving production-grade AI applications to ensure reliability.