AI Engineer (LLM orchestration & Prompts)

Senture, LLC; India; Remote; INR 1,600,000 - 2,500,000; Full time

Job summary

A global digital transformation leader in India is seeking a highly experienced professional to architect LLM-powered applications and develop advanced AI workflows. The ideal candidate will have over 8 years of experience in software or AI engineering, specifically with LLMs and Generative AI. Responsibilities include developing robust applications and ensuring systems are reliable and high-quality. Join a diverse team committed to innovation and excellence in the field of AI.

Qualifications

• 8+ years of software engineering or AI engineering experience.
• 3+ years of hands-on experience specifically with LLMs or Generative AI.
• Experience deploying AI-powered applications in production environments.

Responsibilities

• Develop and productionize LLM-powered applications.
• Architect reasoning flows and prompt structures.
• Seamless connection of LLMs with internal services.

Skills

Software engineering

AI engineering

NLP systems

Python

LangChain

LangGraph

System design

Education

Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or related field

Tools

Vector databases

CI/CD

Job description

Digital Job Description

Maximize Your Impact with TP

Welcome to TP, a global hub of innovation and empowerment, where we redefine the future. With a remarkable €10 billion annual revenue and a global team of 500,000 employees serving 170 countries in over 300 languages, we lead in intelligent, digital-first solutions.

As a Great Place to Work certified in 72 countries, our culture thrives on diversity, equity, and inclusion. We value your unique perspective and believe that your talent is the missing piece that completes our vision for a brighter, digitally driven tomorrow.

The Opportunity

In this role, you will be the architect of the "reasoning layers" that power our most sophisticated products. This isn't just about writing prompts; it’s about building resilient, multi-step AI workflows that interact with global enterprise data in real-time.

You will join a high-caliber team dedicated to solving the challenges of reliability, grounding, and scale in Generative AI. If you are an experienced engineer who loves the intersection of software craftsmanship and the frontier of LLMs—from RAG pipelines to autonomous agentic workflows—this is where you’ll make your mark.

The Responsibilities

• Develop and productionize LLM-powered applications for complex automation, knowledge retrieval, and advanced conversational workflows.
• Architect the underlying reasoning flows and prompt structures to ensure model outputs are consistent, reliable, and high-quality.
• Seamlessly connect LLMs with internal services, proprietary APIs, and diverse enterprise data sources.
• Develop robust prompt templates, few-shot examples, and structured output formats (JSON/Pydantic) to ensure system interoperability.
• Implement validation layers and fallback strategies to mitigate hallucinations and ensure response safety.
• Refine and optimize prompts based on real-world usage patterns, user feedback, and edge-case analysis.
• Design end-to-end retrieval pipelines using vector databases and semantic search technologies.
• Improve "response grounding" by optimizing document chunking strategies, embedding models, and dynamic context windows.
• Integrate structured and unstructured enterprise knowledge bases into fluid AI workflows.
• Build multi-step AI "agents" using frameworks like LangChain or LangGraph that can autonomously interact with tools and APIs.
• Ensure all AI workflows are observable, maintainable, and meet enterprise-grade uptime requirements.
• Establish rigorous evaluation frameworks to measure response accuracy, hallucination rates, and overall quality.
• Monitor and optimize for latency, token consumption, and cost-to-performance ratios.

The Qualifications

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or a related technical field.
• 8+ years of software engineering or AI engineering experience, demonstrating a high level of technical maturity and system design capability.
• 3+ years of hands‑on experience specifically with LLMs, Generative AI, or advanced NLP systems.
• A clear track record of deploying AI-powered applications into high‑stakes production environments (not just POCs).
• Deep proficiency in LangChain, LangGraph, or similar frameworks for managing complex AI state and logic.
• Experience with vector databases (e.g., Pinecone, Weaviate, Milvus) and semantic search implementation.
• Strong command of Python and modern software engineering practices (CI/CD, unit testing for AI, and observability).

Pre-Employment Screenings

By TP policy, employment in this position will be contingent on your successful completion of and passage of a comprehensive background check, including global sanctions and watchlist screening.

Important | Policy on Unsolicited Third-Party Candidate Submissions

TP does not accept candidate submissions from unsolicited third parties, including recruiters or headhunters. Applications will not be considered, and no contractual association will be established through such submissions.

Culture & Belonging

At TP, we are committed to fostering a diverse, equitable, and inclusive workplace. We welcome individuals from all backgrounds and lifestyles and do not discriminate on the basis of gender identity or expression, sexual orientation, race, religion, age, national origin, citizenship, disability, pregnancy status, veteran status, or other differences.

#LI-RR1 #LI-Remote