Senior Agentic AI Engineer

We are looking for an experienced Agentic AI Engineer to design and build production-grade AI agents and agentic workflows for enterprise applications. The ideal candidate combines strong software engineering fundamentals with hands-on experience building solutions using LLMs, agent frameworks, enterprise data, APIs and cloud services.

This role goes beyond prompt engineering. You will build AI systems that can reason, retrieve context, use tools, interact with enterprise applications, execute workflows and operate safely with appropriate human oversight.

Qualifications & Experience

• Bachelor’s degree in Computer Science, Information Systems, Engineering or equivalent experience.
• 8+ years of overall software engineering experience, with strong experience building enterprise applications, APIs and distributed systems.
• Hands-on experience designing and developing Generative AI / Agentic AI applications using commercial and/or open-source LLMs.
• Strong understanding of agent architecture and orchestration, including planning, routing, tool calling, multi-step workflows, state management, retries, exception handling and human-in-the-loop patterns.
• Experience with agent/LLM frameworks such as LangGraph, LangChain, Semantic Kernel, CrewAI, AutoGen or similar frameworks.
• Strong experience with Python and API development using frameworks such as FastAPI; Java, Node.js/TypeScript or similar enterprise development experience is a plus.
• Experience building RAG and context-engineering solutions, including embeddings, vector search, chunking, retrieval, reranking, grounding and citations.
• Experience designing and exposing tools/APIs for AI agents, including REST APIs, structured tool calling and Model Context Protocol (MCP).
• Strong understanding of prompt and specification engineering, structured outputs, JSON schemas and techniques for controlling LLM behavior.
• Experience implementing guardrails, authorization, approval gates and deterministic validations around probabilistic AI components.
• Experience developing AI evaluation frameworks, including evaluation datasets, deterministic checks, LLM-as-judge, regression testing and quality metrics.
• Understanding of AI observability and tracing across prompts, model calls, retrieval, tool execution, latency, token usage and failures.
• Experience working with AWS, preferably services such as Bedrock, Lambda, API Gateway, S3, DynamoDB, ECS/EKS and CloudWatch.
• Strong SQL skills and experience working with relational, NoSQL and vector databases.
• Experience integrating AI solutions with enterprise applications, APIs, databases, document repositories and workflow platforms.
• Experience with Docker, Kubernetes and production deployment of scalable cloud-native applications.
• Strong hands-on experience with CI/CD practices and tools such as GitHub/GitLab, Jenkins and automated testing frameworks.
• Experience troubleshooting production issues, identifying performance bottlenecks and optimizing latency, reliability and cost.
• Ability to write configurable, maintainable, secure and testable production-quality code.
• Experience working in Agile delivery environments.
• Property & Casualty insurance domain experience is a plus.

What You Will Do

• Design and develop enterprise AI agents and agentic workflows that automate complex business processes.
• Decompose business workflows into appropriate combinations of agents, LLM calls, deterministic services, rules and human decisions.
• Build agents capable of retrieving enterprise knowledge, reasoning over context and securely calling business systems and APIs.
• Design multi-agent and orchestrated workflows involving branching, parallel execution, retries, state management and long-running processes.
• Build reusable agent skills, tools and MCP integrations with clearly defined contracts and permissions.
• Develop RAG and context-engineering solutions using enterprise documents, structured data and application context.
• Implement guardrails, validation, security controls and human approval points for high-impact actions.
• Build evaluation suites to measure accuracy, groundedness, task completion, tool-use correctness and regression before releases.
• Implement tracing and monitoring to understand what an agent did, why it did it and what systems/data it accessed.
• Evaluate and select models based on task quality, latency and cost rather than relying on a single model for every workflow.
• Collaborate with Product Owners, Business Analysts, architects, domain SMEs and engineering teams to translate business intent into executable agent specifications.
• Mentor engineers and establish engineering standards and reusable patterns for enterprise Agentic AI development.

Soft Skills

• Excellent written and verbal communication skills.
• Strong analytical and problem-solving ability.
• Comfortable working with ambiguous problems and asking the questions necessary to turn them into clear specifications.
• Strong teamwork and interpersonal skills with the ability to collaborate across business and technology teams.
• Self-motivated and able to work effectively in a fast-moving environment where technologies, requirements and priorities evolve rapidly.
• Experience working in an onsite/offshore delivery model.
• Ability to mentor other engineers and raise the team’s technical and engineering standards.

What We Are Looking For

We are not looking only for someone who knows how to call an LLM API.

We are looking for engineers who understand how to turn AI into reliable enterprise software—combining agents, models, data, APIs, deterministic logic, security, evaluation, observability and human judgment.