Job Description:
AI Engineer
As a core member of the launch team, you will build and deploy the production AI services that power Eve’s intelligence. You will own the end-to-end lifecycle of critical AI features—from integrating them into our backend to ensuring they are scalable, reliable, and observable in production. This role is focused on the application layer of our AI stack, connecting our models and agentic frameworks to the user experience.
Responsibilities:
- Agent & Tool Integration: Implement and harden the tool-use capabilities for Eve's specialized agents (`ResearchAgent`, `CommunicationAgent`), building robust adapters for web APIs, database lookups, and internal services.
- Model Routing & Orchestration: Extend and optimize the `LLMRouter` to handle dynamic model selection (local DeepSeek vs. cloud providers like GPT-4o), implement resilient prompt chains with fallbacks, and manage context across complex, multi-turn conversations.
- Real-time Voice & Streaming: Build and maintain the high-throughput, low-latency streaming endpoints for our voice pipeline, ensuring seamless integration between our front-end, the Parakeet STT service, and the FishAudio TTS service.
- RAG Pipeline Implementation: Work with the ML Engineer to productionize the RAG system, building the API layer that retrieves context from our vector database and injects it into agent prompts.
- Production Ownership: Implement comprehensive logging, tracing (e.g., LangSmith), and metrics for all AI services. Participate in on-call rotation to diagnose and resolve production issues related to latency, cost spikes, or model performance degradation.
Preferred Qualifications:
- 4+ years of hands-on experience shipping production-level ML/LLM systems. This is not a research role; we need proven builders who have weathered the challenges of deploying and maintaining live AI products.
- Expertise in both TypeScript/Node.js and Python. Must be able to seamlessly bridge the gap between the application layer (TypeScript) and the ML/AI layer (Python).
- Deep experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex) and a strong understanding of their underlying principles to build and customize complex agentic workflows.
- Proven experience with high-performance LLM serving and inference optimization (e.g., vLLM, TensorRT-LLM). They must understand how to minimize latency for real-time applications like the Neural Nexus.
- Hands-on experience with vector databases (e.g., ChromaDB, Pinecone, Weaviate) and the full lifecycle of Retrieval-Augmented Generation (RAG) systems, from data ingestion to retrieval optimization.
- A strong sense of production ownership. Must have experience with observability stacks (logging, metrics, tracing with tools like LangSmith or Arize AI) and participating in on-call rotations for critical AI systems.
Benefits Package (Canada & UAE)
Global (all roles)
- Stock options (standard 4‑year vest, 1‑year cliff; refresh grants annually)
- Competitive salaries
- Quarterly employee travel coupon
- Paid time off: 20 days + local holidays (min), flexible sick days
- Medical, dental, and vision insurance (company‑sponsored)
- Life insurance and disability benefits
- Fitness discounts / wellness stipend
- Tech equipment (laptop + peripherals; home‑office stipend)
- Community involvement: 4 hours/month paid volunteer time
- Company‑sponsored tech talks and happy hours
Canada‑specific
- RRSP matching (company match up to 4% base)
- Health Spending Account (HSA) or Lifestyle Spending Account (LSA)
- Parental leave top‑ups aligned to provincial standards
- Flexible work: hybrid/remote within jurisdiction
UAE‑specific
- Health insurance compliant with UAE regulations (dependents eligibility by level)
- Annual flight allowance (by level), relocation support
- End‑of‑service gratuity per UAE labor law
- Housing/transport allowances (as cash or consolidated TC)
- Flexible work: hybrid/remote within jurisdiction
