Key Responsibilities

Develop and deploy Generative AI applications using LLMs (GPT, Llama, etc.)

Build and maintain LLM pipelines, including prompt engineering and fine-tuning

Design and implement end-to-end AI/ML workflows (data → model → deployment)

Work with vector databases for semantic search and retrieval (RAG architecture)

Implement LLMOps practices for monitoring, evaluation, and versioning

Integrate LLMs into applications via APIs and microservices

Optimize model performance, cost, and latency

Collaborate with data engineers, product teams, and stakeholders

Conduct testing, validation, and debugging of AI models

Ensure security, compliance, and responsible AI practices

Required Skills & Qualifications

Technical Skills

Strong proficiency in Python

Hands-on experience with Generative AI & LLM frameworks:

OpenAI / Azure OpenAI APIs

Hugging Face Transformers

LangChain / LlamaIndex

Experience with prompt engineering and RAG (Retrieval-Augmented Generation)

Familiarity with vector databases (FAISS, Pinecone, Weaviate, Chroma)

Knowledge of ML/DL frameworks (PyTorch / TensorFlow – basics)

Experience in API development (FastAPI, Flask)

Understanding of RESTful services and microservices architecture

• Primary skills:Technology->Data Science->Machine Learning,Technology->Geographical Information System->Spatial Databases->SQL Server,Technology->Machine Learning->Python

Preferred Skills (Nice-to-Have)

Experience with fine-tuning LLMs / parameter-efficient tuning (LoRA, PEFT)

Knowledge of multimodal AI (text, image, audio)

Exposure to cloud platforms (AWS, Azure, GCP)

Experience with Kubernetes and scalable deployments

Knowledge of data engineering tools (Spark, Kafka)

Familiarity with vector search optimization and embeddings

Understanding of AI governance, ethics, and compliance

Experience with chatbots, copilots, or conversational AI systems