Lead Engineer - AI/ML

Develop and implement machine learning and NLP models for real-world applications.

Build Generative AI applications using LLMs such as OpenAI, Llama, and Mistral.

Design and optimize Retrieval-Augmented Generation (RAG) pipelines.

Work with embedding models, prompt engineering, and model fine-tuning.

Apply ML techniques like classification, regression, clustering, and dimensionality reduction.

Develop LLM workflows using LangChain and LangGraph.

Work on agent-based and multi-agent systems, including basic A2A communication.

Experiment with CrewAI and agent orchestration frameworks.

Build and maintain AI-backed APIs using FastAPI, Flask, or Django.

Integrate ML models into applications with scalable REST services.

Work with data using Python, SQL, PostgreSQL, and ArangoDB.

Perform data processing and analysis using Pandas and NumPy.

Use vector databases such as FAISS, Milvus, or Chroma.

Deployment & MLOps

Containerize and deploy AI services using Docker.

Use Git and Linux for version control and development workflows.

Support on‑premise deployments and basic model monitoring.

Security & Access Control

Implement RBAC, authentication, and authorization using JWT and SSO.

Follow secure coding and data‑protection best practices.