Senior / Principal AI Engineer – GenAI, Agentic AI & ML-Ops

We are looking for talented professionals with strong expertise in Generative AI, Agentic AI systems, and Machine Learning to design and build intelligent, scalable, and production-grade AI solutions. This includes working on LLM-based applications, multi-agent systems, and end-to-end ML pipelines.

Key Responsibilities:

1. Machine Learning & Statistical Modelling • Build and optimize ML models (regression, classification, clustering, time series, sequence models) • Perform feature engineering, EDA, and data quality analysis • Apply statistical modelling, experimental design, and performance evaluation • Develop scalable ML pipelines for structured and unstructured data

2. GenAI / LLM Application Development • Develop GenAI applications using LangChain, LangGraph • Build and optimize RAG pipelines (retrieval, reranking, chunking, vector DBs like FAISS, OpenSearch, PGVector) • Design advanced prompt engineering strategies (ReAct, Chain-of-Thought, self-reflection loops) • Integrate LLM solutions with enterprise applications, APIs, and data systems

3. Agentic Systems & MCP • Design and implement agentic workflows (tool-calling agents, planner–executor systems, multi-agent architectures) • Build and manage Model Context Protocol (MCP) servers for tool integration • Implement memory architectures (episodic, semantic, vector-based memory) • Develop and evaluate agent systems using LangSmith

4. Evaluation, Observability & Quality • Define evaluation frameworks for ML and GenAI systems (precision@k, recall@k, grounding quality, hallucination checks) • Use LangSmith for tracing, monitoring, regression testing, and system-level evaluation • Ensure reliability, scalability, and transparency of AI systems

5. Cloud ML-Ops & Engineering • Manage ML lifecycle: model deployment, monitoring, data drift, and concept drift • Work across AWS / Azure / Databricks environments • Collaborate with engineering teams for production deployment • Follow best practices in Git, GitHub, Docker, and documentation

6. Leadership & Collaboration (for senior roles) • Drive technical direction and architecture decisions • Collaborate with product teams to define AI features and solutions • Mentor teams and contribute to AI strategy

Required Skills & Experience: • 5–15 years of experience in Machine Learning, GenAI, and ML-Ops • Strong programming expertise in Python, PySpark, SQL • Experience with Scikit-Learn, XGBoost, LightGBM, Random Forest • Hands-on expertise with LangChain, LangGraph, LangSmith • Experience with RAG architectures and vector databases • Exposure to multi-agent systems and orchestration frameworks • Experience with MLflow / SageMaker / Databricks • Strong understanding of LLM evaluation, safety, and performance optimization • Proven experience building production-grade AI/GenAI systems