Artificial Intelligence Engineer

AI Engineer – Generative AI / Agentic Systems

We are looking for a hands-on AI Engineer to design, build, and deploy production-grade Generative AI applications and agentic systems. This role is ideal for an engineer who combines strong Python/backend engineering with practical experience building LLM-powered applications, RAG systems, AI agents, MCP integrations, and evaluation frameworks.

The engineer will work closely with business users and engineering teams to take AI use cases from prototype through production, building reliable systems that can operate against proprietary enterprise data and integrate with existing applications and workflows. The profile is modeled around experience such as building and scaling production GenAI platforms, RAG/retrieval systems, multi-agent applications, and AI-enabled business workflows.

Responsibilities

• Design and develop production Generative AI and LLM-powered applications using Python.
• Build agentic and multi-agent systems capable of reasoning across enterprise data and invoking specialized tools and APIs.
• Design and implement RAG architectures, including document ingestion, retrieval, grounding, chunking/indexing strategies, and retrieval optimization.
• Develop MCP servers and tools that securely expose enterprise data and functionality to AI agents.
• Build backend AI services and APIs using technologies such as Python, FastAPI and Pydantic.
• Integrate commercial and open-source LLMs through APIs and cloud AI platforms.
• Develop prompt-management and context-engineering frameworks supporting versioning, testing, experimentation, and controlled production releases.
• Create robust LLM evaluation frameworks, including retrieval precision/recall, answer-quality metrics, golden datasets, LLM-as-judge approaches, and automated evaluation within CI/CD pipelines.
• Design AI workflows with appropriate guardrails, validation, error handling, monitoring and observability.
• Build ingestion pipelines that transform documents, emails, research and other unstructured information into formats usable by AI applications.
• Deploy and operate AI services in cloud environments using technologies such as AWS ECS, Lambda, S3, DynamoDB, RDS and Bedrock.
• Partner directly with business SMEs to understand workflows, identify high-value AI use cases, translate requirements into technical solutions, and iterate based on user feedback.
• Evaluate emerging AI frameworks, models and tooling and make architecture decisions around build-vs-buy, model providers and orchestration frameworks.
• Take ownership across the full lifecycle from POC → architecture → development → evaluation → deployment → monitoring → production optimization.

This emphasis reflects the candidate's work taking GenAI systems from prototype to production, building Python/FastAPI backends, developing RAG and MCP architectures, creating multi-agent systems, establishing evaluation frameworks, and partnering directly with front-office users.

Required Experience

• Strong professional software engineering experience with Python.
• Hands-on experience developing production Generative AI / LLM applications.
• Strong understanding of RAG, agentic systems, tool calling, MCP, prompt engineering and context engineering.
• Experience designing and integrating REST APIs and backend services.
• Experience with AI/LLM evaluation, including automated evaluation and quality measurement.
• Strong understanding of production engineering practices including testing, Git, CI/CD, monitoring and observability.
• Experience deploying applications to a major cloud platform, preferably AWS.
• Experience working with structured and unstructured enterprise data.
• Ability to work directly with business stakeholders and translate ambiguous business problems into production AI solutions.
• Strong software architecture and problem-solving skills.

Preferred Experience

Experience with FastAPI, FastMCP, Pydantic, LangGraph, Arize Phoenix, DeepEval, MLflow, Claude SDK, AWS Bedrock, Snowflake, DynamoDB and containerized cloud deployments is highly desirable. Experience building AI applications in financial services, investment management, Capital Markets, research or trading environments would also be a strong plus.

The key profile I would target here is not a traditional ML/Data Scientist. It's a strong Python software engineer who has moved deeply into applied GenAI and is actually building production RAG, agents, MCP, evaluation and LLM applications end-to-end.