Senior AI Engineer

Responsibilities

We're building an AI platform that powers intelligent automation, agentic workflows, and large-scale retrieval services across our enterprise. Looking for an engineer who understands both the systems layer and the AI protocol layer.

• Design and develop production-grade AI services and APIs that integrate with multiple LLM providers (OpenAI, Anthropic, open-source models). Build the core infrastructure, not just applications on top of it.

• Create an enterprise-grade agentic framework for orchestration, retrieval, and collaboration between multiple AI agents. This means understanding how agents communicate, how to handle state, how to route requests efficiently.

• Implement knowledge retrieval systems and semantic search using vector databases (Qdrant, ElasticSearch). You'll work on the actual retrieval logic and optimization, not just plugging in a vector DB.

• Build shared Python libraries and SDKs used across multiple services. Write code that other engineers will depend on, which means it needs to be clean, well-tested, and properly documented.

• Drive observability and validation for AI systems. Build monitoring that actually tells you what's happening with model performance, latency, cache hit rates, and failure modes.

Requirements

Qualifications / Experience / Technical Skills

• You've built production services with proper observability, deployment pipelines, monitoring, and security. You know how to run reliable systems at scale, handle data-intensive workloads, and debug distributed systems when things break.

• You understand how things work under the hood. Standard libraries over frameworks. You can read a protocol spec and implement against it directly. When you need to integrate with an API, you understand what's happening on the wire.

• Senior-level experience in Go or Python (5+ years in one, comfortable in the other). If you're coming from Go, you should know Python well enough to work in it for the first few quarters and vice versa. You'll be writing Python for core platform work.

• Strong grasp of distributed systems, API design, and data-driven architectures. You've worked with both relational and non-relational databases (PostgreSQL, Elastic, vector databases).

AI/LLM Experience

• You've worked with LLMs at the protocol level. You understand message structures, caching strategies, tool calling mechanics, and streaming responses. You know what's happening during inference, not just what the SDK abstracts away.

• You've integrated with OpenAI-compatible APIs, ideally building directly against the protocol rather than relying on high-level frameworks. You can evaluate an LLM response, understand token usage, and optimize for latency and cost.

• Experience with semantic retrieval, vector databases, or knowledge graph architectures is valuable. You understand the tradeoffs between different retrieval strategies.

Working Style

• You learn fast and stay current. You monitor what's happening in AI infrastructure globally and can evaluate new approaches quickly.

• You participate in technical design discussions, code reviews, and mentor other engineers. You can explain complex technical concepts clearly to both engineers and non-technical stakeholders.

• You're comfortable with the full development lifecycle: design, implementation, deployment, monitoring, and continuous improvement.

Environment

You'll work with Python, FastAPI, LLM APIs, vector databases, PostgreSQL, Kubernetes, and modern CI/CD tooling. We use frameworks where appropriate (LiteLLM, Langfuse, etc.), but prefer engineers who understand what's underneath and can work at the protocol level when needed.

To stand out in our hiring process, please take the time to respond to the Job Application Questions below with concise yet informative answers. All submissions are personally reviewed by the Hiring Team, not evaluated by AI.

Job Req ID: 2406