We are looking for an AI Engineer with 3+ years of hands-on experience building AI-enabled solutions using both open-source and closed-source AI models. This role is focused on practical implementation: designing, integrating, and deploying AI-powered features, workflows, and applications that solve real business problems.
The ideal candidate should have strong experience working with modern LLMs, AI APIs, open-source model ecosystems, and production-grade AI application development. Traditional machine learning experience is a plus, but not mandatory.
Key Responsibilities
- Build AI-enabled applications, tools, and workflows using large language models and related technologies.
- Work with both closed-source models such as OpenAI, Anthropic, Google Gemini, Azure OpenAI, etc., and open-source models such as Llama, Mistral, Qwen, DeepSeek, Falcon, or similar.
- Design and implement LLM-powered solutions including chatbots, copilots, automation agents, document intelligence systems, search experiences, and workflow assistants.
- Build and optimize RAG pipelines using embeddings, vector databases, chunking strategies, retrieval logic, and prompt orchestration.
- Integrate AI models into web applications, backend systems, APIs, and internal tools.
- Evaluate model outputs for accuracy, reliability, latency, cost, and user experience.
- Experiment with prompt engineering, function calling, tool use, agents, structured outputs, and AI workflow orchestration.
- Collaborate with product, engineering, and business teams to convert requirements into practical AI solutions.
- Stay updated with emerging AI models, frameworks, tools, and deployment patterns.
Required Skills and Experience
- 3+ years of practical engineering experience, with strong hands-on exposure to AI-enabled solution development.
- Experience building real projects using LLMs or generative AI technologies.
- Strong programming skills in Python and/or JavaScript/TypeScript.
- Experience working with closed-source AI APIs such as OpenAI, Anthropic, Gemini, Azure OpenAI, or similar.
- Experience working with open-source models through Hugging Face, Ollama, vLLM, LM Studio, or similar tools.
- Practical understanding of prompt engineering, embeddings, RAG, vector databases, and LLM application architecture.
- Experience with frameworks such as LangChain, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar.
- Familiarity with REST APIs, databases, Git, cloud platforms, and production deployment workflows.
- Ability to evaluate AI outputs, debug model behavior, and improve solution quality through iteration.
- Strong problem-solving skills and ability to work independently on AI projects.
Pay: ₹30,000.00 - ₹40,000.00 per month
Work Location: In person
