AI Engineer (Indore)

AI Engineer (Indore)

10 Aug
|
Pepcus
|
Indore

10 Aug

Pepcus

Indore

Job Location

Indore, India

Experience

3+ years sections

- title

About Pepcus paragraphs

- Artificial Intelligence is no longer about integrating a language model into an application. Building reliable AI products requires thoughtful system design, intelligent retrieval strategies, orchestration frameworks, continuous evaluation, and engineering discipline.
- At Pepcus, we build production-ready AI solutions that solve real business problems. From enterprise knowledge assistants and autonomous agents to intelligent workflow automation and AI-powered developer tools, we engineer AI systems that are scalable, reliable, measurable, and designed for enterprise adoption.
- We are looking for an AI Engineer who enjoys solving complex engineering challenges, experimenting with emerging AI capabilities, and building intelligent systems that go far beyond prompt engineering.

- title The Role paragraphs

- As an AI Engineer, you will design, build, and optimize production-grade AI applications using modern Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic workflows, and AI evaluation frameworks.
- You'll work closely with Product Managers, Architects, and Software Engineers to build AI systems that balance accuracy, latency, scalability, cost, and user experience. You will play a key role in transforming cutting-edge AI research into reliable enterprise-grade solutions that create measurable business value.
- This role is ideal for engineers who are passionate about applying AI engineering principles to build production-ready systems rather than simply integrating AI APIs.

- title

Responsibilities items

- Design, develop, and deploy production-ready AI applications using modern LLMs and enterprise AI architectures.
- Build Retrieval-Augmented Generation (RAG) pipelines that deliver accurate, grounded, and context-aware responses.
- Develop intelligent agent workflows, multi-agent systems, and AI-powered automation solutions.
- Design AI orchestration pipelines, workflow architectures, and stateful agent interactions.
- Implement AI evaluation frameworks to continuously measure and improve quality, accuracy, reliability, and safety.
- Optimize AI systems for latency, inference cost, scalability, and overall user experience.
- Integrate enterprise knowledge sources,



structured data, and external systems into AI workflows.
- Collaborate with Product Managers, Architects, and Engineering teams to design and deliver scalable AI solutions.
- Leverage modern AI engineering practices to continuously experiment, benchmark, evaluate, and improve AI applications.
- Stay current with emerging AI models, frameworks, and engineering best practices.

- title

Required Qualifications items

- 3+ years of software engineering experience, including at least 1-2 years building Generative AI or LLM-powered applications.
- Strong Python programming skills and experience building production-quality software.
- Experience designing and implementing Retrieval-Augmented Generation (RAG) architectures and enterprise retrieval systems.
- Hands-on experience with contemporary LLM ecosystems such as OpenAI, Anthropic, Google Gemini, Azure OpenAI, OpenRouter, or open-weight models.
- Experience building intelligent agent workflows, autonomous agents, or multi-agent systems.
- Strong understanding of prompt engineering, context engineering, model selection, and LLM optimization techniques.
- Experience implementing AI evaluation strategies, including response scoring, regression testing, hallucination detection, or LLM-as-a-Judge evaluation patterns.
- Experience designing AI orchestration workflows using modern frameworks and engineering patterns.
- Strong understanding of software engineering fundamentals, distributed systems, APIs, and cloud-native application development.
- Experience deploying AI applications into production environments and monitoring their performance.

- title

Preferred Qualifications items

- Experience with AI engineering frameworks such as LangGraph, LlamaIndex, LangChain, DSPy, CrewAI, AutoGen, or similar technologies.
- Experience implementing Model Context Protocol (MCP) or AI gateway architectures.
- Knowledge of vector databases, hybrid search,



semantic search, embeddings, metadata filtering, and advanced retrieval strategies.
- Experience with AI observability, prompt optimization, structured outputs, function calling, and model routing.
- Familiarity with event-driven architectures, workflow orchestration, and distributed AI systems.
- Experience fine-tuning models, working with open-source LLMs, or deploying inference infrastructure.
- Experience building AI-powered enterprise applications within Healthcare, HRTech, FinTech, or other regulated industries.

- title What Makes You Successful paragraphs

- Successful AI Engineers understand that building intelligent systems is fundamentally an engineering discipline. They focus on reliability, scalability, evaluation, and continuous improvement rather than chasing the latest AI trends.
- They know when retrieval is more effective than a larger model, when autonomous agents provide real business value, and how to objectively measure AI quality through robust evaluation strategies. They combine curiosity, experimentation, and sound engineering judgment to build AI systems that deliver meaningful business outcomes.

- title

Why Join Pepcus items

- Build next-generation AI products that solve real-world business problems across Healthcare, HRTech, FinTech, and other regulated industries.
- Work with experienced AI Architects, Product Managers, and Engineering leaders on cutting-edge AI initiatives.
- Design and deploy enterprise-scale AI systems using modern LLMs, RAG architectures, autonomous agents, and AI evaluation frameworks.
- Gain hands-on experience with the latest AI technologies while building production-ready solutions that create measurable customer value.
- Be part of an engineering-first culture that values innovation, continuous learning, experimentation, technical excellence, and responsible AI development.

- title

Employment Type paragraphs

- Full-time

- note true paragraphs

- Pepcus is an equal opportunity employer. We consider all qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other protected characteristic under applicable law.

mailto:[email protected]

📌 AI Engineer (Indore)
🏢 Pepcus
📍 Indore

Reply to this offer

Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.

Subscribe to this job alert:

Get the latest job offers by email for: ai engineer (indore) / indore

Subscribe to this job alert:

Get the latest job offers by email for: ai engineer (indore) / indore