Lead AI Engineer

Description :

- Build scalable, secure, and high-performance AI systems using modern backend engineering and distributed architecture principles.

- Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, prompt engineering frameworks, and LLM orchestration workflows.

- Integrate AI solutions with enterprise APIs, vector databases, structured/unstructured data sources, and third-party platforms.

- Improve system scalability, inference performance, latency, reliability, and operational efficiency for production AI workloads.

- Develop RESTful APIs and backend services for AI applications using FastAPI or equivalent frameworks.

- Collaborate with product, engineering, and business stakeholders to translate functional requirements into AI-driven solutions.

- Manage the complete software development lifecycle including architecture, development, deployment, monitoring, testing, and optimization.

- Implement observability, logging, monitoring, and reliability best practices for AI systems in production

environments.

- Deploy and manage AI applications in containerized and cloud-native environments using Docker and Kubernetes.

Required Skills & Experience :

- 2- 4 years of practical experience building enterprise AI Engineering or LLM-based applications.

- Strong experience with modern LLM orchestration frameworks including :

1. LangChain

2. LlamaIndex

3. LangGraph

- Hands-on experience with vector databases and semantic search platforms such as :

1. Pinecone

2. FAISS

3. Weaviate

- Strong understanding of :

1. Retrieval-Augmented Generation (RAG)

2. Prompt Engineering

3. Embeddings

4. Semantic Search

5. Context-Aware AI Systems

- Experience building scalable backend APIs and AI services using :

1. FastAPI

2. RESTful APIs

3. Microservices Architecture

- Experience deploying scalable AI applications using :

1. Docker

2. Kubernetes

3. Containerized Cloud Environments

- Strong familiarity with cloud platforms including :

1. AWS

2. Azure

3. GCP

Preferred Qualifications :

- Exposure to real-time inference systems and streaming architectures.

- Experience implementing MLOps best practices including :

1. CI/CD Automation

2. Model Monitoring

3. AI Deployment Pipelines

4. Version Control

- Strong understanding of scalable AI infrastructure, distributed systems, and cloud-native engineering.

- Experience working in Agile/Scrum development environments.