Lead AI Engineer

Role & responsibilities

About the Role

We are looking for a Lead AI Engineer to lead the design, development, and delivery of production-grade AI solutions across our products and client projects. The ideal candidate is a strong hands-on engineer with deep experience in Generative AI, Large Language Models (LLMs), RAG, AI Agents, AI workflows, and AI-powered applications, combined with the ability to guide a team of AI engineers and make sound architectural decisions. This role requires someone who can move comfortably between AI strategy, architecture, hands-on development, technical leadership, experimentation, and production delivery.

You will be responsible for establishing engineering standards for our AI initiatives and helping the team turn emerging AI capabilities into reliable, scalable business solutions.

Key Responsibilities

1. AI Architecture & Engineering

• Lead the architecture and development of production-grade AI applications and platforms.
• Design solutions using LLMs, RAG, AI Agents, tool calling, function calling, MCP, vector databases, and AI orchestration frameworks.
• Evaluate and select appropriate models, frameworks, infrastructure, and AI services based on business and technical requirements.
• Design scalable architectures for multi-tenant AI applications and SaaS platforms.
• Establish patterns for prompt management, context management, memory, retrieval, tool use, and agent orchestration.
• Ensure AI solutions are secure, observable, maintainable, and cost-efficient.
• Define technical standards and reusable components for the AI engineering team.

2. Generative AI & LLM Development

• Work extensively with commercial and open-source LLMs.
• Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, retrieval, reranking, and contextual generation.
• Develop intelligent AI agents capable of reasoning, planning, tool execution, and multi-step workflows.
• Implement structured outputs, function calling, tool calling, and model integrations.
• Develop prompt engineering strategies and reusable prompt patterns.
• Evaluate model performance and identify opportunities for fine-tuning, model optimization, or alternative approaches.
• Stay current with rapidly evolving developments in Generative AI and translate relevant advancements into practical solutions.

3. AI Agents, Automation & MCP

• Design and implement AI agents that interact with enterprise systems and external tools.
• Build integrations using MCP (Model Context Protocol) and other tool-integration mechanisms.
• Develop AI-powered workflows for applications such as customer support, e-commerce, business operations, knowledge management, and software engineering.
• Establish guardrails and approval mechanisms for autonomous AI actions.
• Design human-in-the-loop workflows where required.
• Ensure agentic systems behave predictably and safely in production.

4. Team Leadership

• Lead and mentor a team of AI engineers.
• Conduct technical reviews, architecture reviews, and code reviews.
• Break down complex AI initiatives into achievable engineering tasks.
• Guide engineers on architecture, implementation approaches, and best practices.
• Identify technical gaps and establish learning/development plans for the team.
• Promote engineering discipline, documentation, testing, and knowledge sharing.
• Help build and maintain a strong AI engineering culture within the organization.

5. AI Evaluation & Quality

• Establish methodologies for evaluating LLM and AI application performance.
• Define metrics for accuracy, relevance, hallucination, latency, cost, reliability, and task completion.
• Build automated evaluation and regression-testing pipelines for AI systems.
• Implement observability for prompts, model responses, retrieval quality, tool execution, latency, and token usage.
• Continuously improve AI systems based on evaluation results and production feedback.

6. Production & MLOps

• Take AI solutions from prototype to production.
• Design deployment architectures for cloud and self-hosted AI workloads.
• Work with engineering teams on CI/CD, containerization, monitoring, logging, and infrastructure.
• Optimize AI workloads for performance, scalability, and cost.
• Evaluate GPU requirements and infrastructure for both cloud and self-hosted models.
• Establish appropriate practices for model versioning, prompt versioning, configuration management, and AI release management.

7. Security, Governance & Responsible AI

• Ensure AI applications follow organizational security and privacy standards.
• Design controls against prompt injection, data leakage, unauthorized tool execution, and other AI-specific threats.
• Establish appropriate access controls and tenant isolation for AI applications.
• Contribute to AI governance, security reviews, and compliance requirements.
• Ensure sensitive information is handled appropriately throughout AI pipelines.

8. Innovation & Technical Research

• Continuously evaluate emerging AI technologies, models, frameworks, and platforms.
• Conduct technical POCs and experiments to validate new approaches.
• Identify opportunities to apply AI to existing products and business processes.
• Evaluate when to use APIs, open-source models, fine-tuning, RAG, agents, or traditional software approaches.
• Convert successful experiments into reusable production capabilities.

Required Technical Skills

AI Frameworks & Platforms

Experience with one or more of: LangChain, LangGraph, LlamaIndex, Semantic Kernel, OpenAI APIs, Anthropic APIs, Google Gemini APIs, Azure AI, AWS AI/ML services, Hugging Face, vLLM, Ollama or similar local inference platforms

Data & Retrieval

Experience with technologies such as: PostgreSQL, Vector databases, pgvector, Qdrant, Pinecone, Weaviate, Elasticsearch / OpenSearch, Redis, Search and retrieval systems

Cloud & Infrastructure

Experience with one or more: AWS, Azure, GCP, Docker, Kubernetes, GPU infrastructure, CI/CD platforms

Experience

10+ years of software engineering experience, with significant recent experience in AI/ML and Generative AI of min 4+ years.

• Proven experience building and deploying production AI applications.
• Experience leading or mentoring engineers.
• Experience owning technical architecture for AI initiatives.