Senior Data Scientist

Job Description

Role Overview

We are looking for a Senior Agentic AI Engineer with strong hands-on software engineering experience and practical expertise in Generative AI and Agentic AI solutions.

The successful candidate will design, build, integrate, and productionize intelligent AI solutions leveraging Large Language Models (LLMs), agentic workflows, enterprise data, APIs, and business applications.

This is a hands-on engineering role requiring strong implementation and problem-solving capabilities, with ownership of solutions from technical design through production deployment.

A Data Engineering background or strong understanding of enterprise data platforms is a significant advantage, particularly for building AI solutions that interact with complex enterprise data ecosystems.

Key Responsibilities

Design and develop Agentic AI applications and AI-driven workflows using LLMs.

Build single-agent and multi-agent solutions, including orchestration, reasoning, planning, memory, and tool usage.

Develop solutions leveraging RAG, embeddings, vector search, knowledge bases, and enterprise data sources.

Implement LLM tool/function calling and integrate agents with APIs, databases, enterprise applications, and external services.

Work with Agentic AI frameworks such as LangGraph/LangChain, Microsoft Semantic Kernel, AutoGen, or equivalent.

Develop scalable backend components and APIs using Python and modern software engineering practices.

Implement security, guardrails, evaluation, monitoring, observability, and Responsible AI practices.

Design evaluation approaches for agent quality, accuracy, reliability, performance, and cost.

Deploy and operate AI solutions within cloud and containerized environments.

Collaborate with AI/Data Architects, Data Engineers, Product Owners, and business stakeholders to translate business use cases into scalable solutions.

Independently own significant technical components and contribute to solution design and engineering decisions.

Mentor junior engineers and contribute to engineering standards, reusable components, and best practices.

Mandatory Skills & Experience

5+ years of professional experience in software engineering, AI engineering, data engineering, or related technical roles.

Strong hands-on development skills in Python.

Practical experience building applications using Generative AI / LLMs.

Hands-on experience developing Agentic AI solutions, intelligent workflows, or advanced LLM-based applications.

Strong understanding of:

LLMs and prompt engineering

Agent orchestration and tool/function calling

RAG architectures

Embeddings and vector search

Context and memory management

API and enterprise system integration

Experience with at least one Agentic AI / GenAI framework such as LangGraph, LangChain, Semantic Kernel, AutoGen, or equivalent.

Strong software engineering fundamentals including API development, Git, testing, CI/CD, and production-quality coding practices.

Experience with Docker and/or Kubernetes.

Experience with at least one major cloud platform: Azure, AWS, or GCP.

Strong analytical, troubleshooting, and problem-solving skills.

Ability to work independently and take end-to-end technical ownership of assigned components.

Strong Advantage: Data Engineering

Candidates with a Data Engineering background or strong data engineering foundation will have a significant advantage.

Relevant experience may include:

Data pipelines, ETL/ELT, and data integration patterns

Working with structured, semi-structured, and unstructured data

Strong SQL and database experience

Data lakes, lakehouses, warehouses, and modern data platforms

Technologies such as Databricks, Spark, Snowflake, Microsoft Fabric, Azure Data Factory, AWS Glue, or equivalent

Data quality, metadata, governance, lineage, and security

Integrating enterprise data platforms with GenAI, RAG, and Agentic AI solutions

Additional Nice-to-Have Skills

Experience with enterprise GenAI platforms such as Azure AI Foundry / Azure OpenAI, AWS Bedrock, or equivalent.

Experience with vector search/vector database technologies such as Azure AI Search, pgvector, Pinecone, Weaviate, Milvus, or equivalent.

Knowledge of MLOps / LLMOps practices.

Experience with LLM/agent evaluation, tracing, monitoring, and observability.

Understanding of cloud-native and microservices architectures.

Experience implementing Responsible AI, security, content safety, and AI governance controls.

Experience delivering AI solutions within large enterprise environments.

Candidate Profile

We are looking for someone who is:

Hands-on and engineering focused, rather than purely conceptual or architectural.

Able to take an Agentic AI use case from technical design through implementation and production deployment.

Comfortable working across AI, software engineering, cloud, and data technologies.

Able to evaluate and quickly adopt emerging Agentic AI technologies where appropriate.

Capable of working independently while collaborating effectively with architects and multidisciplinary teams.

Able to mentor less experienced engineers and contribute to reusable engineering assets and standards.