We are seeking a Lead AI Engineer to design and implement advanced AI applications, including chatbots and agent workflows.
You will work closely with clients to understand their needs and deliver large language model (LLM) driven solutions that provide measurable business value. This role involves developing robust data pipelines, refining AI system performance, and staying updated on the latest LLM technologies. Join us to contribute your expertise in AI engineering and help shape innovative solutions for our clients.
Responsibilities
- Design and implement end-to-end AI applications such as chatbots, Q&A platforms, and agent workflows
- Collaborate directly with clients to identify needs and recommend LLM-based AI solutions
- Develop and manage data pipelines, prompt strategies, and datasets to support AI model accuracy
- Evaluate and improve AI system outputs for accuracy, security, scalability, and regulatory compliance
- Conduct research and rapid prototyping to validate AI technical feasibility and business impact
- Stay informed on evolving LLM technologies, frameworks, and methodologies to enhance solutions
- Deploy AI solutions with attention to performance, cost, and maintainability
- Assess generative AI quality using retrieval, classification, and LLM-based evaluation metrics
- Work with cross-functional teams to integrate AI capabilities effectively
- Maintain documentation for AI applications and workflows
- Provide technical guidance and mentorship to junior team members
- Participate in client meetings to present AI strategies and progress
- Monitor AI system performance and troubleshoot issues
- Ensure compliance with industry standards and best practices
- Contribute to continuous improvement of AI development processes
Requirements
- Proficiency in Python programming and experience with web frameworks such as FastAPI
- Understanding of the AI application development lifecycle
- Experience with rapid UI prototyping tools like Streamlit or Gradio
- Familiarity with major LLM platforms and APIs, including OpenAI, Anthropic, Amazon Bedrock, and Gemini
- Knowledge of advanced AI integration patterns, such as retrieval-augmented generation and agents
- Experience deploying AI solutions at scale with focus on performance and cost optimization
- Ability to evaluate generative AI output quality using various metrics and evaluation methods
- Demonstrated experience delivering AI and machine learning solutions
- Strong analytical and problem-solving skills with attention to detail
- Effective communication and collaboration skills to engage with clients and teams
- Strong written and verbal English communication skills (B2+)
Nice to have
- Experience designing experiments, running A/B tests, and iterating models based on feedback
- Understanding of retrieval systems including keyword and vector search with ranking algorithms
- Familiarity with emerging protocols like MCP, A2A, and ACP
- Experience deploying AI solutions on cloud platforms such as Azure OpenAI, Amazon Bedrock, or GCP Vertex AI
- Knowledge of enterprise AI platforms like AWS AgentCore, Databricks AgentBricks, Google Agents Space, or Azure AI Foundry