AI/ML Engineer

AI/ML Engineer

We are seeking AI/ML engineers to design, deploy, and scale intelligent systems that seamlessly integrate Large Language Models (LLMs) with production-grade machine learning pipelines.

Key Responsibility Area:

• Build scalable RAG pipelines by developing chunking logic, generating embeddings, and implementing hybrid retrieval using PGVector/Qdrant and BM25.
• Design, evaluate, and optimize LLM prompt flows (OpenAI, Mistral, Anthropic, etc.) including function-calling, fallback logic, and safety guardrails.
• Deploy and serve GenAI and ML models (Scikit-learn, XGBoost, LightGBM) as REST/gRPC APIs using FastAPI/Triton, fully containerized in Docker.
• Automate retraining, validation, and deployment pipelines using tools like MLflow, Airflow, and DVC, ensuring continuous model improvement.
• Monitor performance and data quality in real time using Prometheus/Grafana, and design drift detection with alerting and rollback mechanisms.
• Optimize system performance for latency, cost, and reliability while ensuring scalability through CI/CD pipelines, Git, and container orchestration.
• Apply strong Python engineering practices, leveraging LangChain, LlamaIndex, and reusable SDK design for model orchestration and feature engineering.
• Maintain high code quality through testing frameworks (pytest), version control, and modern DevOps workflows.
• Collaborate with cross-functional teams to integrate GenAI and ML services into production systems and continuously refine them through A/B testing and feedback loops.