AI Engineer

Job Description

Key Responsibilities : Develop, train, and fine-tune large language models and generative architectures (LLMs, VAEs, Transformers, GANs) Integrate models with applications using LangChain, LlamaIndex, RAG, and other frameworks Design LLM-based agents for specific use cases: summarization, classification, scoring, Q&A, translation Build prompt templates and semantic memory flows using vector databases like Pinecone or FAISS Collaborate with backend and data teams to ingest data from PDFs, APIs, structured databases, and JSON files Benchmark model outputs and run experiments to optimize cost, performance, and quality Stay on top of AI research and rapidly implement useful techniques in production environments Write clear, modular, reusable code with documentation and test coverage Troubleshoot model-related deployment or inference issues Technical Skills Required : Strong Python programming skills Experience with Transformers, Hugging Face, OpenAI/Anthropic APIs, Med-GEMMA, or similar foundation models Experience with agentic frameworks: LangChain, LlamaIndex, LangGraph, semantic RAG Familiarity with Vector database experience (Pinecone, FAISS, Weaviate, or similar) Comfortable with prompt engineering, few-shot learning, fine-tuning basics Ability to process and clean unstructured data (PDFs, notes, research papers, etc.) Understanding of NLP metrics and model evaluation techniques Bonus: experience with biomedical or clinical data (PubMed, ClinicalTrials.gov, etc.) Bonus: experience with deploying models via FastAPI, Docker, or Streamlit Personal Attributes : Curiosity and willingness to learn new models and tools quickly Attention to detail and commitment to quality Ownership mindsetyou care about the outcome, not just the code Ability to work independently and push through ambiguity Passion for building usable AI, not just research prototypes Strong communication and collaboration skills across tech and domain teams