Senior AI Engineer
We are seeking a Senior AI Engineer to design and implement comprehensive AI applications, including chatbots and agent workflows.
You will work closely with clients to tailor large language model solutions that meet their specific needs. This role involves developing data pipelines, refining AI systems for performance and compliance, and staying updated with emerging AI technologies. Join us to contribute to cutting-edge AI projects and enhance client outcomes with your expertise.
Responsibilities
- Design and maintain AI applications, including chatbots, Q&A platforms, and agent workflows
- Work with clients to understand their needs, identify opportunities, and recommend LLM-driven solutions
- Build and manage data pipelines, prompt strategies, and datasets for effective AI models
- Assess and optimize AI system performance to ensure outputs are accurate, secure, scalable, and compliant with industry standards
- Conduct research and prototype rapidly to test feasibility and demonstrate AI solutions' business value
- Keep up-to-date with advancements in LLM technologies, frameworks, and methodologies to enhance outcomes
Requirements
- Proficiency in Python with experience using web frameworks like FastAPI or similar
- Knowledge of the AI application development lifecycle
- Skills in rapid UI prototyping with frameworks such as Streamlit or Gradio
- Familiarity with major LLM platforms and APIs (OpenAI, Anthropic, Amazon Bedrock, Gemini) and frameworks like LangGraph or LlamaIndex
- Understanding of advanced AI integration patterns such as RAG and Agents
- Background in deploying AI solutions at scale with attention to performance and cost-efficiency
- Competency in evaluating generative AI quality using metrics like retrieval scores, classification scores, or LLM-based evaluations
- Expertise in AI engineering and delivering ML-based solutions
- Strong problem-solving adaptability with a high attention to detail
- Excellent collaboration and interpersonal communication abilities
Nice to have
- Skills in designing experiments, performing A/B tests, and refining models based on feedback
- Knowledge of retrieval systems (keyword search, vector search, embeddings) and ranking algorithms
- Familiarity with new protocols such as MCP, A2A, ACP, etc.
- Proficiency in deploying to cloud AI platforms (Azure OpenAI, Amazon Bedrock, GCP Vertex AI) or on-premise infrastructures like vLLM
- Background in using enterprise AI platforms such as AWS AgentCore, Databricks AgentBricks, Google Agents Space, or Azure AI Foundry
- Capability to apply observability and monitoring tools or frameworks
