What you will be doing :

- Design, build, and deploy LLM-driven applications (e.g., document summarization, RAG-based QA, chatbots).

- Work with open-source LLMs using platforms like Ollama and Hugging Face.

- Implement LangChain and LangGraph workflows for multi-step, multi-agent task resolution.

- Build and optimize RAG (Retrieval-Augmented Generation) systems using vector databases.

- Collaborate with cross-functional teams to ship features to production.

- Stay up-to-date with the latest in open-source LLMs, model optimization (LoRA, quantization), and multi-modal AI.

Required Skills :

- 3-5 years of hands-on experience in AI/ML engineering.

- Proficient in Python, PyTorch, and Hugging Face Transformers.

- Proven experience with LangChain and LangGraph for LLM workflows.

- Familiarity with Ollama, Mistral, LLaMA, or similar open-source LLMs.

- Experience working with vector stores (Qdrant, Pinecone, Weaviate, FAISS).

- Skilled in backend integration using FastAPI, Docker, and cloud platforms.

- Solid grasp of NLP, LLM reasoning, prompt engineering, and document parsing.

Nice-to-Have :

- Experience with LangServe, OpenAI tool/function calling, or agent orchestration.

- Background in multi-modal AI (e.g., image + text analysis).

- Familiarity with MLOps tools (MLflow, Weights & Biases, Airflow).

- Contributions to open-source GenAI projects.

- Understanding of LLM safety, security, and alignment principles.