Senior Data Scientist

Job Description:

At AT&T we’re redefining the future of communication by connecting people to greater possibility with expertise, simplicity, and inspiration. At the heart of our purpose lies a diverse workforce of 200,000 people and a culture that aspires to serve customers first, act boldly, move faster, and win as one.

Our Product Development group, part of AT&T’s Technology Services (ATS) organization, is responsible for building software-based products, services, and platforms that our customers love and need. Harnessing technology and rebuilding software expertise, the team is inspiring simplicity with projects that deliver revenue and cost savings opportunities.

Job Overview

AT&T is building a new era of intelligent automation. We are looking for a highly skilled Senior Data Scientist with advanced Python expertise to design, develop, and integrate intelligent systems focused on large language models (LLMs), prompt engineering, and advanced context management. You will architect context-rich AI solutions, craft effective prompts, and ensure seamless agent interactions using frameworks like LangGraph and AutoGen, with robust observability and experimentation powered by Langfuse.

As a Senior Data Scientist, you will architect, build, and deploy context-driven AI solutions that transform how entire organizations work and deliver value. You’ll leverage LLMs, Retrieval-Augmented Generation (RAG), and next‑gen AI agents to automate complex workflows, driving productivity, efficiency, and measurable outcomes. You will also produce clear technical R&D reports that document experiments, metrics, trade-offs, and recommendations for stakeholders.

Core Responsibilities

• Design, optimize, and evaluate prompts for LLMs to achieve precise, contextually appropriate outputs across diverse use cases.

• Architect and implement dynamic context management strategies, including session memory, retrieval-augmented generation, and user personalization to enhance agent performance.

• Build and manage agentic workflows and multi-agent systems using frameworks such as LangGraph and AutoGen.

• Integrate, fine-tune, and orchestrate LLMs within Python-based applications, leveraging APIs and custom pipelines for scalable deployment.

• Implement observability, tracing, evaluation, and experiment management using Langfuse; define and track key metrics (quality, latency, cost).

• Develop and maintain robust backend services, APIs, and (optionally) front-end interfaces to deliver end‑to‑end AI applications.

• Produce concise, technically rigorous R&D reports that document problem framing, methodology, experiment design, results, and recommended next steps.

• Work closely with product, data science, and engineering teams to define requirements, run prompt/agent experiments, and iterate quickly on solutions.

• Apply and advocate best practices in software engineering, code quality, testing, DevOps, and secure, ethical AI automation.

Skills, Knowledge, and Experience

Day-to-Day

• Design and develop agentic AI solutions and intelligent automation workflows using LLMs, prompt engineering, context management, and multi-agent orchestration (AutoGen, LangGraph).

• Collaborate with cross-functional teams to define and refine requirements, run experiments, and iterate on AI-driven solutions.

• Architect and integrate scalable, production-grade Python applications for AI agent deployment.

• Use Langfuse to trace, evaluate, and compare prompt and agent versions; maintain experiment logs and dashboards.

• Participate in code reviews, contribute to best practices, and mentor peers on AI automation technologies and frameworks.

• Produce clear technical R&D reports summarizing approach, experiments, findings, and recommendations.

Technical Skills

• Advanced skills in Python, including FastAPI, async I/O, typing/mypy, packaging, testing (pytest), performance profiling, and dependency management.

• Advanced skills in AutoGen (multi-ag