Role Overview
We are looking for a hands-on Lead Engineer - AI to design, build, and deliver scalable AI-powered applications and platforms. The role requires strong engineering leadership, practical experience with LLMs, RAG, agents, prompt engineering, model integration, MLOps, APIs, and cloud-native deployment, along with the ability to mentor engineers and accelerate delivery using AI-assisted development tools.
Key Responsibilities
- Lead the design and development of AI/GenAI applications, LLM-powered workflows, agents, copilots, and intelligent automation solutions.
- Build production-grade solutions using Python, APIs, LLMs, vector databases, RAG pipelines, embeddings, and orchestration frameworks.
- Design and implement Retrieval-Augmented Generation, prompt engineering, function calling, tool use, context management, and evaluation workflows.
- Integrate AI capabilities with enterprise applications, APIs, databases, event-driven platforms, and business workflows.
- Define architecture patterns for AI solutions, including model selection, data flow, retrieval strategy, guardrails, observability, and cost optimization.
- Remain hands-on with coding, prototyping, debugging, code reviews, performance tuning, and production issue resolution.
- Establish engineering standards for AI solution development, including testing, evaluation, monitoring, security, privacy, and responsible AI controls.
- Mentor engineers and collaborate with architects, data scientists, ML engineers, product teams, security, DevOps, and business stakeholders.
- Use approved AI tools such as GitHub Copilot, Cursor, Microsoft Copilot, or equivalent to accelerate coding, testing, documentation, and solution design.
- Review and validate AI-generated code and model outputs to ensure correctness, explainability, security, and business alignment.
Required Skills And Experience
- 8+ years of software engineering experience, including experience in a technical leadership role.
- Strong hands-on experience with Python and backend/API development.
- Practical experience building AI/GenAI solutions using LLMs, RAG, embeddings, vector databases, prompt engineering, and agents.
- Experience with frameworks and platforms such as LangChain, LlamaIndex, Semantic Kernel, Azure OpenAI, OpenAI APIs, Hugging Face, or similar.
- Strong understanding of AI application architecture, model integration, data pipelines, and production deployment.
- Experience with vector databases such as Azure AI Search, Pinecone, Weaviate, Milvus, Chroma, or FAISS.
- Good understanding of MLOps/LLMOps concepts including model evaluation, versioning, monitoring, drift detection, feedback loops, and automated testing.
- Strong knowledge of REST APIs, microservices, cloud platforms, CI/CD, Docker, Kubernetes/OpenShift, and observability.
- Understanding of AI security, privacy, hallucination mitigation, prompt injection risks, access controls, and responsible AI principles.
- Ability to translate business problems into AI use cases with measurable outcomes.
- Strong problem-solving, stakeholder management, mentoring, and communication skills.
Preferred Skills
- Experience with Azure AI Foundry, Azure OpenAI, Microsoft.Extensions.AI, Semantic Kernel, or MLflow.
- Experience designing enterprise copilots, autonomous agents, AI assistants, or workflow automation platforms.
- Knowledge of traditional ML, NLP, deep learning, feature engineering, and model-serving patterns.
- Experience with Kafka, event-driven architecture, data lakes, data warehouses, or real-time analytics platforms.
- Familiarity with AI governance, model risk management, auditability, and compliance requirements.
- Experience defining AI evaluation metrics such as accuracy, groundedness, relevance, toxicity, latency, cost, and user feedback.
- Exposure to frontend or full-stack development for building AI-enabled user experiences.
Success Measures
- Delivery of production-ready AI solutions with measurable business impact.
- Improved development speed and quality through responsible use of AI-assisted engineering.
- Reliable AI outputs through strong evaluation, monitoring, and guardrail implementation.
- Reduction in manual effort through automation, copilots, and intelligent workflows.
- Secure and compliant AI solution delivery aligned with enterprise architecture standards.
- Improved team capability through mentoring, reusable patterns, and technical leadership.
