About this role
Soliton Technologies seeks a Python AI Engineer to build and deploy production-ready generative AI applications for customers across sectors including semiconductors, medical devices, automotive and Industry 4.0. The role integrates LLMs, data pipelines and inference systems, with an emphasis on RAG, model performance and responsible deployment.
Responsibilities
- Develop generative AI applications in Python and FastAPI, using LLM frameworks such as LangChain and LlamaIndex. Build and optimize RAG pipelines with vector databases, knowledge graphs, graph-based retrieval, re-ranking, prompt engineering and context engineering.
- Prepare and transform structured and unstructured data. Run offline inference with tools such as Ollama or Hugging Face and models including Llama and Mistral; integrate online providers such as OpenAI, Anthropic or GCP.
- Deploy containerized applications with Docker. Implement guardrails, monitor workflows with tools such as MLflow or Arize Phoenix, evaluate performance with TruLens or custom systems, and improve results using metrics and user feedback.
Requirements
- Bachelor’s or master’s degree in computer science, engineering or a related field; proven AI/ML engineering experience and at least 3 years building applications with Python and asynchronous programming.
- Experience with generative AI, FastAPI, LLM frameworks, RAG and retrieval optimization; ability to work with documents, PDFs and structured data. Familiarity with vector databases and AI agents; experience with Azure or AWS, Docker, CI/CD, SQL and NoSQL databases. Understanding of online and offline LLMs, evaluation, monitoring and observability, plus strong problem-solving, communication and teamwork skills.
Preferred
Experience with MCP clients and servers; multimodal LLMs for image and voice; cloud or on-premises deployment; and fine-tuning techniques and data preparation.
Location and benefits: This full-time role is based in Bangalore or Coimbatore and requires working from the office for the first 12 months. Remote or hybrid work may be considered afterward, depending on performance and business needs. Benefits include flexible work hours subject to job requirements, health insurance for employees and families, gym and cycle allowances, and profit-sharing eligibility from the second year.