AIML Engineer: LLM Apps, RAG Pipelines & Python

Tata Consultancy Services; Milford (OH); On-site; USD 140,000 - 165,000; Full time

Benefits offered by this job

Discretionary Annual Incentive

Comprehensive Medical Coverage: Health

Dental & Vision

Disability Planning & Insurance

Commuter Benefits

Certification & Training Reimbursement

Vacation & Holidays

Job summary

Tata Consultancy Services (TCS) is seeking an engineering leader to build and deploy production-grade backend systems in Python and craft LLM-powered applications. You will architect RAG pipelines and agentic workflows, leveraging embeddings and vector databases to deliver scalable AI solutions.

You will design multi-step, tool-using agents, integrate AI with APIs and cloud platforms, and establish robust evaluation and performance strategies across latency, accuracy, and cost concerns.

Qualifications

• Strong Python expertise for production backend systems.
• Hands-on experience building applications with LLMs, including prompt engineering.
• Proven experience with RAG architectures, embeddings, and vector databases.
• Experience with agentic frameworks like LangChain, LangGraph, AutoGen.
• Strong system design skills for cloud-based applications.

Responsibilities

• Architect and deliver end-to-end LLM-powered applications and agentic workflows.
• Design and implement RAG pipelines over enterprise data using embeddings and vector databases.
• Build multi-step, tool-using agents with planning, execution, memory.
• Integrate AI systems with APIs, backend services, and cloud platforms.
• Establish evaluation, reliability, and performance strategies (accuracy, latency, cost).

Skills

Python backend development

LLM application development

RAG architectures and vector databases

Agentic frameworks (LangChain; LangGen

Education

Bachelor of Computer Science or related field

Tools

LangChain

LangGraph

AutoGen

Job description

Tata Consultancy Services (TCS) is seeking an engineering leader to build and deploy production-grade backend systems in Python and craft LLM-powered applications. You will architect RAG pipelines and agentic workflows, leveraging embeddings and vector databases to deliver scalable AI solutions.

You will design multi-step, tool-using agents, integrate AI with APIs and cloud platforms, and establish robust evaluation and performance strategies across latency, accuracy, and cost concerns.