Job Location: Pune
Experience: 2+ Years
We are seeking a motivated and skilled AI Engineer to join our innovative team. The ideal candidate will have a strong passion for building practical AI applications and a drive to stay at the forefront of the rapidly evolving field of generative AI. If you enjoy working with cutting-edge models and frameworks to solve real-world problems, we encourage you to apply.
Key Responsibilities
- Develop, train, and fine-tune large language models and other generative architectures such as VAEs, Transformers, and GANs.
- Integrate AI models with applications using frameworks like LangChain, LlamaIndex, and CrewAI.
- Design and build specialized LLM-based agents for tasks including summarization, classification, Q&A, and translation.
- Create prompt templates and manage semantic memory flows with vector databases like Pinecone or FAISS.
- Work alongside backend and data teams to process and ingest data from various sources, including PDFs, APIs, and structured databases.
- Benchmark model performance and conduct experiments to optimize for cost, efficiency, and quality.
- Stay current with the latest advancements in AI research and apply new techniques to our production environment.
- Produce clean, modular, and reusable code with comprehensive documentation and test coverage.
- Troubleshoot and resolve any issues related to model deployment or inference.
Required Technical Skills
- Strong proficiency in Python programming.
- Hands-on experience with foundation models (e.g., Transformers, Hugging Face, OpenAI/Anthropic/Gemini APIs).
- Experience with agentic frameworks such as LangChain, LlamaIndex, LangGraph, or CrewAI.
- Familiarity with vector databases like Pinecone, FAISS, or Weaviate.
- Solid understanding of prompt engineering, few-shot learning, and the fundamentals of fine-tuning.
- Proven ability to process and clean unstructured data from sources like PDFs and research papers.
- Knowledge of NLP metrics and techniques for model evaluation.
Desired Personal Attributes
- A strong sense of curiosity and the ability to quickly learn new models and tools.
Meticulous attention to detail and a strong commitment to delivering high-quality work.
An ownership mindset with a focus on outcomes, not just writing code.
The ability to work independently, navigating ambiguity to push projects forward.
A passion for building usable AI solutions rather than just research prototypes.
Excellent communication and collaboration skills to work effectively with technical and domain-focused teams.
Bonus Points
- Experience deploying models using FastAPI, Docker, or Streamlit.
- Previous experience building or deploying LLMs into a production environment.
- Professional experience in the healthcare domain.
- A portfolio of personal projects, GitHub repositories, or AI experiments that showcase your passion and skills.