AI Platforms Developer - JB-619

We are looking for a mid-level software engineer to help design, build our AI platform and AI agents, and implement it for our customers. You will work on the core building blocks of our AI stack: LLMs, agents, MCP-based tools, AI gateways, and evaluation systems, and make sure they come together into robust, secure, and scalable solutions.

You’ll participate in high-level design discussions, then roll up your sleeves and write the code, integrations, and infrastructure needed to bring those designs to life. We are not looking for a “pure developer” or someone overly senior; we want a strong developer with good systems thinking who is excited to learn, grow, and gradually take ownership of more complex architecture decisions.

What you’ll do

• Develop AI agents and AI-based solutions for our customers.
• Help design and implement core components of our AI platform, including agents, tools, and integrations with multiple LLM providers.
• Help define and evolve the overall AI platform architecture (data flows, components, APIs, gateways) together with senior engineers and architects.
• Implement and configure AI gateways and orchestration layers (e.g., routing between different models/providers, fallback strategies, cost/latency optimizations).
• Work with modern AI protocols and standards (such as MCP and similar) to connect tools, data sources, and services into coherent agentic workflows.
• Build and maintain APIs and services that expose AI capabilities to internal teams and customers (REST/GraphQL/SDKs).
• Design and implement evaluation and monitoring systems for AI features, including logging, metrics, quality evaluation pipelines, and feedback collection.
• Participate in customer implementation projects: adapt the platform to customer environments, integrate with their systems, and support rollout.
• Contribute to internal documentation, playbooks, and best practices for building and operating AI-powered systems.
• Stay up to date with developments in LLMs, agents, protocols, and AI infrastructure, and recommend improvements to our platform.

What we’re looking for

• 3-5 years of professional experience in full‑stack development.
• Strong coding skills in at least one modern language (e.g., Python, TypeScript/Node.js, Java, or similar) and experience building production services.
• Solid understanding of core AI/LLM concepts and terminology: LLMs, agents, tools, MCP (Model Context Protocol) or similar standards, vector search/embeddings, and basic prompt design.
• Experience integrating with LLM/AI APIs (e.g., OpenAI, Azure OpenAI, Gemini, Anthropic, or others), including authentication, rate-limiting, and error handling.
• Experience with Kubernetes and running workloads in a Kubernetes environment.
• Good grasp of system and data architecture fundamentals: services and APIs, data flows, caching, async processing, and basic scalability patterns.
• Familiarity with AI gateways, proxies, or orchestration layers and interest in going deep into AI-specific routing, safety, and policy enforcement.
• Exposure to evaluation/monitoring concepts for AI systems (e.g., metrics, test cases, regression checks, human-in-the-loop review) or strong willingness to learn.
• Ability to see the big picture: understand business and product goals, and translate them into architecture and implementation plans.
• Comfortable working in greenfield/ambiguous environments, designing and building components from scratch and iterating based on feedback.
• Strong communication skills and team mindset; able to explain technical decisions and trade-offs clearly and work well with both technical and non-technical stakeholders.

Nice to have

• Hands-on experience with agent frameworks or tool-calling systems (e.g., LangChain, LangGraph, LlamaIndex, custom agent frameworks).
• Experience designing or operating AI gateways and orchestration platforms (multi-model routing, policy management, observability).
• Practical experience implementing AI evaluation and safety frameworks (e.g., automated evals, red-teaming, guardrails, content filters).
• Experience with Cloud and DevOps methodologies.
• Familiarity with enterprise AI productivity tools (e.g., Microsoft 365 Copilot, Gemini Enterprise, ChatGPT Enterprise) and how they fit into a broader AI platform.
• Background in working with multiple customer environments (consulting, integrator, or B2B product company), including requirements gathering and solution design.
• Basic knowledge of security, privacy, and compliance considerations for AI systems (data residency, PII handling, RBAC, audit logging).