Key Responsibilities:

- Build and deploy scalable LLM, RAG, and agent-based systems.

- Architect LLM inference and deployment pipelines.

- Optimize models for efficient and cost-effective production.

- Collaborate with data science, research, and product teams.

- Ensure clean code, testing, reproducibility, and CI/CD.

- Mentor junior engineers and drive engineering best practices.

- Ensure ethical, secure, and responsible AI development.

Required Skills:

- Advanced Python with strong fundamentals in NumPy, Pandas, scikit-learn.

- Deep learning expertise in PyTorch / TensorFlow.

- Hands-on with LLM frameworks: Hugging Face Transformers, LangChain (prompting & fine-tuning).

- Strong experience with Agentic AI frameworks: AutoGen, CrewAI, LangGraph.

- Expertise in RAG pipelines, semantic search, vector databases.

- Strong software engineering practices: microservices, TDD, concurrency.

- Ability to rapidly prototype and productionize GenAI solutions.

Good-to-Have Skills:

- Model optimization: Quantization (GPTQ, AWQ), pruning, distillation.

- Multimodal AI (text, vision, audio): CLIP, BLIP, Whisper, LLaVA.

- LLM serving using FastAPI and vector DBs (FAISS, Pinecone, Chroma).

- CI/CD pipelines, Airflow, Docker, Kubernetes / Helm.

- Cloud AI deployments on AWS / Azure / GCP (e.g., SageMaker).

- MLOps & tracking: Git, MLflow.

- Data pipelines & ELT/ETL using Snowflake.