AI Technical Lead

Non-Negotiable Skills

Python (real coding ability, not theoretical)

Hands-on LLM integration (not just coursework)

Cloud deployment experience (AWS or Azure)

RAG understanding

API development experience

Role Summary

We are looking for a motivated AI Engineer with hands-on experience in Python and cloud platforms (AWS or Azure) to help design, build, and deploy Generative AI solutions. This role will work closely with senior engineers, data teams, and business stakeholders to build AI-powered applications including LLM integrations, RAG pipelines, prompt workflows, and AI-driven automation solutions. This is a hands-on engineering role — not research-only.

Key Responsibilities

Generative AI development in this role involves building and integrating applications that leverage large language models. The engineer will be responsible for developing retrieval-augmented generation (RAG) pipelines, implementing prompt engineering techniques, and ensuring structured output generation. A key part of the work will be integrating AI services through APIs such as OpenAI, Azure OpenAI, or AWS Bedrock, while also creating AI-powered chatbots, assistants, and internal productivity tools that enhance business workflows.

Python engineering is central to the position. The candidate will be expected to write clean, scalable code that supports AI workflows, while also developing REST APIs using frameworks like FastAPI or Flask. Working with JSON, structured data, embeddings, and vector stores will be routine, as will building data processing scripts that feed into AI pipelines. This requires both technical precision and adaptability to evolving AI technologies.

Cloud deployment is another critical responsibility. The engineer will deploy AI applications using AWS services such as S3, Lambda, Bedrock, EC2, and API Gateway, or Azure services including Azure OpenAI, Functions, Blob Storage, and App Services. Containerization with Docker, even at a basic level, will be necessary to support scalable deployments. In addition, the role requires supporting CI/CD pipelines to ensure smooth and reliable cloud-based operations.

Finally, data and integration tasks will play a significant role. The engineer will work with both structured and unstructured data sources, build connectors to databases such as

PostgreSQL, MySQL, or SQL Server, and assist in creating vector databases using FAISS, Pinecone, or OpenSearch. Supporting model evaluation and logging will also be part of the responsibilities, ensuring that AI systems are monitored, tested, and continuously improved.

Required Skills

The ideal candidate for this role should have between three and six years of experience in software engineering or AI development, with a strong command of Python as the primary programming language. They should be comfortable working with APIs and JSON-based integrations, demonstrating the ability to connect and manage data flows across different systems. A foundational understanding of large language models and generative AI is expected, along with familiarity in prompt engineering, embeddings, and vector search techniques. Hands-on experience with cloud platforms such as AWS or Azure is essential, as the role requires deploying and managing AI applications in these environments. Finally, the candidate should be familiar with Git and collaborative development workflows, ensuring smooth teamwork and version control in a fast-paced engineering setting.

Preferred Qualification - The preferred qualifications for this role highlight experience with modern AI frameworks and cloud-based tools. Candidates should ideally have worked with platforms such as LangChain, LlamaIndex, or similar frameworks that support large language model applications. Familiarity with services like Azure OpenAI or AWS Bedrock is valuable, along with practical knowledge of FastAPI for building APIs and vector databases for managing embeddings and search functionality. In addition to these hands-on skills, a basic understanding of retrieval-augmented generation (RAG) architecture, AI model evaluation techniques, and MLOps fundamentals is expected. These competencies ensure that the engineer can not only build effective AI solutions but also evaluate, manage, and scale them in production environments.Exposure to Databricks is a plus

What We’re Looking For

Strong problem-solving mindset.

Curiosity about emerging AI technologies

Ability to learn quickly and adapt to evolving tools.Comfortable working in a fast-paced, AI-driven environmentStrong communication skills to work with both technical and business teams.

• Experience with LangChain, LlamaIndex, Semantic Kernel, or similar GenAI frameworks.
• Hands-on experience with Azure OpenAI Service or AWS Bedrock.
• Exposure to vector database technologies including Pinecone, Weaviate, ChromaDB, or OpenSearch.
• Experience with Databricks and modern data engineering ecosystems.
• Knowledge of MLOps practices, model evaluation, monitoring, and AI governance.
• Familiarity with Kubernetes, Docker, and scalable cloud-native architectures.
• Experience implementing AI agents, multi-agent frameworks, and workflow orchestration.
• Understanding of Responsible AI, security, and compliance considerations for GenAI solutions.
• Relevant AWS, Azure, or Generative AI certifications.

Non-Negotiable Skills

• Python (strong hands-on coding ability)
• LLM Integration Experience
• RAG Architecture & Vector Search
• Cloud Deployment (AWS or Azure)
• API Development (FastAPI/Flask)
• Prompt Engineering & Embeddings
• Git and Collaborative Development Practices