Senior Analyst - Data Quality

Schneider Electric; Hinoba-an; On-site; PHP 986,000 - 1,380,000; Full time

Job summary

Schneider Electric seeks a Senior Analyst - Data Quality to lead GenAI/LLM application development, focusing on agentic systems, RAG pipelines, and LangChain/LangGraph tooling. You will build intelligent, tool-using agents and evaluation frameworks, integrating LangSmith for monitoring and testing across enterprise environments.

You should bring 5–10 years of experience, strong Python and ML foundations, and hands-on experience with LangChain, LangGraph, LangSmith, and related AI tooling.

Qualifications

• 5–10 years total experience with 2–4+ years GenAI delivery.
• Strong Python and ML foundations including feature engineering and model selection.
• Hands-on with LangChain, LangGraph, LangSmith and RAG patterns; experience with LLMs.

Responsibilities

• GenAI / LLM application development using LangChain and LangGraph.
• Design and implement RAG architectures with memory and vector databases.
• Develop prompts with instruction following, ReAct, and chain-of-thought strategies.
• Evaluate and ground LLM outputs and pipelines using LangSmith for monitoring.
• Build agentic workflows with tool-calling and planner–executor systems.
• Collaborate with backend teams to productionize GenAI and agentic systems.

Skills

Python

LangChain

LangGraph

LangSmith

RAG patterns

Vector databases

MCP tooling

Agent tool integration

ReAct

Tree of Thoughts

Multi-agent orchestration

Education

Bachelor’s or Master’s degree in CS/AI/related field

Tools

FAISS

Azure OpenSearch

OpenSearch

pgvector

AWS / Azure / Databricks

Git / GitOps

Job description

Job Title: Senior Analyst - Data Quality

Function: Digital Innovation & Technology

Location: Powai, Mumbai

Overview

This role demand strong GenAI experience, emerging mastery in Agentic AI Systems, and a good foundation in classical ML.

You will design and build intelligent, tool-using agents, multi-agent systems, RAG pipelines, and LLM-based applications leveraging the LangChain , LangGraph ecosystem, LangSmith for evaluation.

Key Responsibilities

1. GenAI / LLM Application Development

• Build GenAI applications using:
  • LangChain and LangGraph
• Implement RAG architectures with:
  • Retrieval, reranking, chunking, and memory strategies
  • Vector databases such as FAISS, Azure AI Search, OpenSearch, and pgvector
• Design prompt-engineering strategies:
  • Instruction following
  • ReAct (Reasoning + Acting)
  • Chain-of-thought structuring
  • Self-reflection and planning loops
• Evaluation strategy:
  • Implement evaluation frameworks for classical ML and GenAI systems, covering statistical validation, reliability, and robustness.
  • Assess LLM outputs, RAG pipelines, and agent workflows for grounding quality, relevance, and retrieval accuracy, such as recall@k and precision@k.
  • Use LangSmith for tracing, automated evaluations, regression testing, and continuous system-level quality monitoring.

2. Agentic System Architecture

• Build agentic workflows:
  • Tool-calling agents
  • Planner–executor systems
  • Multi-agent communication systems
  • Hierarchical agent architectures
  • Deep agents
• Integrate memory systems:
  • Episodic memory
  • Semantic memory
  • Vector-based long-term knowledge
• Implement evaluation frameworks for agentic systems using LangSmith.

3. Model Context Protocol (MCP) & Tooling

• Implement MCP servers for external tool connectivity.
• Build tools that allow agents to interact with:
  • APIs
  • Code-execution environments
  • Knowledge bases
  • Company applications

4. Classical ML (Foundational DS Skills)

• Apply ML models to structured and unstructured data.
• Conduct feature engineering, model selection, and hyperparameter tuning.
• Build interpretable models where required.

5. Engineering & Integration

• Collaborate with backend engineering teams to seamlessly integrate agentic and GenAI systems into production applications.
• Implement observability, tracing, and monitoring for GenAI workflows using LangSmith to ensure reliability and system-level transparency.

6. Cloud MLOps & Quality

• Monitor ML modelling performance, data drift, concept drift, and model quality.
• Apply hands-on experience across AWS, Azure, or Databricks, with flexibility to work on any cloud platform.
• Adhere to stringent quality assurance and documentation standards using version control and code repositories, such as Git, GitHub, and Markdown.

Required Skills & Experience

• 5–10 years of total experience, including 2–4+ years of hands‑on GenAI delivery.
• Strong Python skills and solid classical ML foundations, including feature engineering, model selection, hyperparameter tuning, tree-based models, and regression.
• Hands‑on expertise in LangChain, LangGraph, LangSmith, RAG patterns, vector databases, MCP tooling, agent tool integration, ReAct, Tree of Thoughts, and multi‑agent orchestration.
• Experience working with LLM APIs and/or open‑source LLMs, including building, evaluating, and debugging production‑grade GenAI pipelines.
• Hands‑on exposure to AWS, Azure, or Databricks; Git/GitOps; MLOps; observability; and model‑drift monitoring.
• Experience deploying enterprise‑grade GenAI solutions in real‑world environments.
• Knowledge of multimodal LLM applications involving vision, speech, or code.
• Familiarity with structured LLM evaluation, including hallucination, safety, reliability, and robustness assessments.

Education and Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Statistics, Mathematics, Engineering, or a related discipline.
• Relevant GenAI, ML, cloud, Databricks, or MLOps certifications are desirable.

Preferred Experience

• Enterprise deployment of complex multi‑agent or multimodal LLM solutions.
• Knowledge of Responsible AI, model governance, data privacy, security, and auditability.
• AI or analytics delivery experience in manufacturing, supply chain, sales, service, channel operations, or digital transformation.

What's in it for me?

• High‑impact work on innovative AI projects that shape business strategy
• Collaborative team culture with talented professionals who support your growth
• Opportunities to expand your expertise and stay at the forefront of AI technology
• Autonomy to guide technical decisions and set your own priorities

Rewards designed for you

Our Total Rewards is our way of saying: We see you and we value you. It’s more than just pay and benefits—it’s a meaningful investment in you. It is designed to help you perform, grow, feel safe, and elevate your potential. The package helps you care for yourself and your family, plan your future, grow your skills and career, collaborate in an inclusive workplace, and contribute to your community. At Schneider Electric, we’re here for what matters most to you. Discover more at our Career Page.

* Country‑specific programs and initiatives may be available.

€40 billion global revenue
+9% organic growth
150 000+ employees in 100+ countries

Schneider Electric aspires to be the most inclusive and caring company in the world, by providing equitable opportunities to everyone, everywhere, and ensuring all employees feel uniquely valued and safe to contribute their best. We mirror the diversity of the communities in which we operate, and inclusion is one of our core values. We believe our differences make us stronger as a company and as individuals and we are committed to championing inclusivity in everything we do.

At Schneider Electric, we uphold the highest standards of ethics and compliance, and we believe that trust is a foundational value. Our Trust Charter is our Code of Conduct and demonstrates our commitment to ethics, safety, sustainability, quality and cybersecurity, underpinning every aspect of our business and our willingness to behave and respond respectfully and in good faith to all our stakeholders. You can find out more about our Trust Charter here.
Schneider Electric is an Equal Opportunity Employer. It is our policy to provide equal employment and advancement opportunities in the areas of recruiting, hiring, training, transferring, and promoting all qualified individuals regardless of race, religion, color, gender, disability, national origin, ancestry, age, military status, sexual orientation, marital status or any other legally protected characteristic or conduct.