About the Role

We're looking for an experienced AI Engineer to help build the next generation of AI-powered products and workflows. This role is focused on applying the latest advances in generative AI—

not training foundation models—to solve real business problems.

You'll design, build, and deploy production-ready AI applications using large language models

(LLMs), retrieval systems, agentic workflows, multimodal models, and modern AI development frameworks. You'll work closely with project managers, UX designers, software engineers, and business stakeholders to rapidly prototype ideas and evolve them into scalable solutions.

This is an ideal role for someone who enjoys moving quickly, experimenting with new technologies, and translating emerging AI capabilities into practical business value.

What You'll Do

- Design, develop, and deploy production-grade AI applications using modern LLMs and multimodal models.
- Build Retrieval-Augmented Generation (RAG) systems leveraging embeddings, vector databases, hybrid search, and knowledge retrieval.
- Develop intelligent agents capable of tool use, function calling, workflow orchestration,

and autonomous task execution.
- Integrate commercial and open-source foundation models including OpenAI, Anthropic,

Google Gemini, and others.
- Evaluate new models, frameworks, and prompting strategies to improve quality,

reliability, latency, and cost.
- Build APIs and backend services that expose AI capabilities to internal and external applications.
- Develop evaluation pipelines and automated testing for prompts, agents, and AI workflows.
- Implement observability, monitoring, guardrails,



and feedback mechanisms for AI systems in production.
- Partner with stakeholders to identify opportunities where AI can improve business processes and employee experiences.
- Contribute to AI architecture decisions, coding standards, and engineering best practices.
- Stay current with the rapidly evolving AI ecosystem and help drive technical innovation across the organization.

Required Qualifications

- 3–5 years of professional software engineering experience.
- 1–3 years building production applications utilizing Large Language Models or

Generative AI technologies.
- Strong proficiency in Python.
- Experience developing AI applications using frameworks such as LangChain,

LangGraph, LlamaIndex, Semantic Kernel, DSPy, or similar.
- Experience implementing RAG architectures and working with vector databases such as

Pinecone, Weaviate, Milvus, Chroma, or pgvector.
- Experience integrating LLM APIs including OpenAI, Anthropic, Google Gemini, or similar platforms.
- Solid understanding of prompt engineering, structured outputs, tool calling, and function invocation.
- Experience building REST APIs and integrating AI capabilities into existing applications.
- Familiarity with cloud platforms (AWS, Google Cloud, or Azure).
- Experience with Docker, Git, CI/CD, automated testing,



and modern software engineering practices.
- Strong communication skills and the ability to explain technical concepts to both technical and non-technical audiences.

Preferred Qualifications

- Experience building autonomous or multi-agent systems.
- Experience using AI evaluation frameworks such as LangSmith, Arize Phoenix, Weights

& Biases, Promptfoo, or DeepEval.
- Experience with MCP (Model Context Protocol), A2A (Agent-to-Agent communication),

or emerging AI interoperability standards.
- Experience with multimodal AI including image, video, speech, or document understanding.
- Experience deploying open-source models using vLLM, Ollama, Hugging Face, or similar inference platforms.
- Familiarity with Kubernetes and scalable cloud infrastructure.
- Background in MLOps, feature engineering, or traditional machine learning.
- Experience building internal AI products, developer tools, or workflow automation platforms.

What Success Looks Like

Within your first year, you'll have:

- Built and launched production AI applications used across the organization.
- Improved existing AI products through experimentation and evaluation.
- Established reusable patterns for agents, RAG systems, and prompt engineering.
- Helped define engineering standards for AI application development.
- Become a trusted technical partner for engineering and business teams.

Technologies We Use

- Python
- OpenAI, Anthropic, Google Gemini
- LangGraph, LangChain, LlamaIndex
- Vector databases (Pinecone, pgvector, Weaviate)
- FastAPI
- Docker
- Kubernetes
- GitHub Actions
- PostgreSQL
- Google Cloud Platform / AWS

📌 Artificial Intelligence Engineer (Delhi)
🏢 The Job Shop - India
📍 Delhi