AI Engineer

Fintricity and Kendra Labs are building enterprise-grade AI infrastructure for the next generation of agentic systems. Our work spans AI gateways, model orchestration, MCP/tool gateways, agent control planes, identity, governance, security, data platforms, code intelligence, and production-grade AI automation.

We are looking for an AI Engineer who can design, build, evaluate, and operate reliable AI systems in real-world enterprise environments. You will work across Fintricity and Kendra Labs to turn frontier AI capability into robust products, internal platforms, customer-facing solutions, and repeatable engineering patterns.

This role is ideal for an engineer who combines strong software engineering fundamentals with hands-on experience in LLMs, agents, retrieval, evaluation, observability, and secure production deployment.

Responsibilities

• Design, build, and maintain AI-powered applications, agents, workflows, and platform components across Fintricity and Kendra Labs.
• Develop production-grade LLM and agentic systems using modern AI engineering patterns, including tool calling, retrieval, orchestration, memory, evaluation, and human-in-the-loop controls.
• Build integrations with enterprise systems, APIs, data sources, model providers, vector stores, code repositories, and MCP-compatible tools.
• Contribute to core Kendra Fabric modules, including AI gateway, agent control plane, MCP/tool gateway, code graph, data plane, identity, security, and governance capabilities.
• Implement robust evaluation pipelines for model quality, agent behaviour, latency, cost, reliability, and safety.
• Design and improve prompt, context, and workflow patterns for repeatable enterprise use cases.
• Build observability, tracing, logging, and debugging capabilities for AI systems in development and production.
• Work with product, engineering, customer, and leadership teams to convert ambiguous business problems into practical AI solutions.
• Apply secure engineering practices for authentication, authorization, data handling, auditability, model access, and tool execution.
• Prototype rapidly, validate assumptions with evidence, and harden successful prototypes into maintainable production systems.
• Document architecture, design decisions, technical trade-offs, and operational runbooks clearly.

Strong software engineering experience in Python, TypeScript, or both.

• Experience with Claude, Gemini, Antigravity, and similar systems to build enterprise applications.
• Practical experience building with LLMs, AI APIs, agent frameworks, RAG systems, tool calling, or workflow orchestration.
• Understanding of modern AI system design: context engineering, retrieval, embeddings, vector databases, structured outputs, function calling, evaluations, guardrails, and observability.
• Experience designing and consuming APIs, working with cloud services, and deploying production systems.
• Ability to reason about reliability, latency, cost, security, privacy, and maintainability in AI applications.
• Strong debugging skills across application code, model behaviour, data pipelines, prompts, and external integrations.
• Familiarity with Git-based development, CI/CD, testing, code review, and engineering documentation.
• Comfortable working in a fast-moving environment where product direction, technical architecture, and customer needs evolve quickly.
• Clear written and verbal communication, with the ability to explain complex AI and engineering concepts to technical and non-technical stakeholders.
• Evidence of ownership: you can take a problem from discovery through design, implementation, testing, deployment, and iteration.

Nice to Haves

• Experience with MCP, agent platforms, tool gateways, AI gateways, model routers, or multi-provider LLM infrastructure.
• Experience with LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, OpenAI Assistants/Responses APIs, Anthropic Claude, Gemini, or comparable frameworks and APIs.
• Experience building enterprise AI, governance, security, compliance, or regulated-industry systems.
• Experience with knowledge graphs, code intelligence, repo analysis, semantic search, or large-codebase understanding.
• Experience with observability tools such as OpenTelemetry, LangSmith, Arize/Phoenix, Helicone, Portkey, or similar platforms.
• Experience with vector databases and search systems such as pgvector, Qdrant, Weaviate, Pinecone, OpenSearch, Elasticsearch, or Vespa.
• Experience with cloud platforms such as AWS, Azure, GCP, Vercel, Cloudflare, or Kubernetes-based environments.
• Experience with identity, access control, SSO, RBAC/ABAC, audit logs, secrets management, or secure tool execution.
• Contributions to open-source AI, developer tooling, infrastructure, or automation projects.
• Prior experience in consulting, product engineering, startup environments, or customer-facing technical delivery.

What Success Looks Like

• You ship useful AI systems that move from prototype to production.
• You make AI behaviour measurable, observable, and improvable.
• You reduce ambiguity by creating clear technical plans, tests, evaluations, and documentation.
• You help establish reusable engineering patterns for Fintricity and Kendra Labs.
• You balance speed with reliability, security, and long-term maintainability