Artificial Intelligence Engineer

Description :

Key Responsibilities :

- Design and implement end-to-end data pipelines for training and fine-tuning LLMs, including dataset creation, cleaning, augmentation, and labeling workflows.

- Apply advanced RAG techniques, prompt engineering, and model fine-tuning (LoRA, PEFT, adapters) for domain-specific use cases.

- Integrate AI models with backend and frontend systems via APIs, batching, caching, and streaming responses.

- Deploy and optimize LLMs & embeddings using APIs and/or open-source models (OpenAI, Anthropic, LLaMA-family, Mistral, etc.).

- Develop and maintain secure AI APIs using FastAPI/gRPC with Kubernetes and CI/CD pipelines.

- Implement safety and compliance layers including prompt injection defenses, hallucination reduction, and PII redaction.

- Collaborate with MLOps and platform engineering teams to ensure scalable deployment using Docker, Kubernetes, and Ray/Serve.

- Leverage frameworks such as LangChain, Hugging Face Transformers, and Azure OpenAI for model orchestration and integration.

- Work with vector databases (FAISS, Pinecone, Milvus) to build efficient retrieval-augmented generation pipelines.

Mandatory Skills :

- Proficiency in Python and experience in LangChain/Hugging Face.

- Hands-on experience with MLOps (Docker, Kubernetes, CI/CD).

- Strong knowledge of model integration and scalable API development.

- Familiarity with safety and compliance mechanisms in AI systems.

Desirable / Plus :

- Prior experience in NBFC / BFSI domain.