AI Engineer (US)

AI Engineer (US)

New York, USA; Philadelphia, Pennsylvania, United States; San Francisco, California, United States

We are investing in agentic AI and need a Senior AI Engineer to lead the design and delivery of these systems. This is a foundational hire: you will own both the agent-facing workstreams — pipelines, orchestration, conversational interfaces — and the underlying context layer that makes them reliable, including memory management, knowledge graph integration, and retrieval infrastructure.

You will work closely with data engineers, project leads, and client stakeholders, and play a key role in shaping how Lynx builds and ships AI solutions at scale.

What This Involves:

• Lead the architecture and delivery of agentic AI systems end-to-end: agents, orchestration, tool use, and multi-step reasoning workflows.
• Own the context layer: design and implement memory architectures (episodic, semantic, working memory) and integrate GraphRAG and knowledge graph retrieval into agentic pipelines.
• Build robust RAG systems — including vector retrieval, graph traversal, and hybrid search — and ensure retrieval quality through evaluation frameworks.
• Translate client requirements into technical designs, presenting approaches and trade-offs to both technical and non-technical stakeholders.
• Define standards and reusable patterns for agentic AI development that other engineers at Lynx can build on.
• Set up observability, evaluation, and monitoring pipelines to ensure AI systems perform correctly in production.

Requirements:

• 5–8 years of software or ML engineering experience, with at least 2–3 years building LLM-based or agentic AI systems in production.
• Deep hands-on experience with agentic frameworks (LangChain, LlamaIndex, AutoGen, CrewAI, or similar) and LLM APIs (OpenAI, Anthropic, etc.).
• Strong understanding of agent design patterns: ReAct, planning loops, tool use, multi-agent coordination, and memory architectures.
• Practical experience with GraphRAG or knowledge graph-based retrieval (e.g., Neo4j, Microsoft GraphRAG) and vector databases (Pinecone, Weaviate, Qdrant, etc.).
• Proficiency in Python and solid software engineering fundamentals: APIs, testing, CI/CD, containerisation (Docker/Kubernetes).
• Experience working in a consulting or client-facing environment — comfortable presenting technical approaches and adapting to ambiguous requirements.
• Strong written and verbal communication skills across distributed, cross-functional teams.

Key Competencies:

• Stakeholder Mentality: Treats the company's and client's goals as their own and is genuinely motivated by its success.
• Organisational Excellence: Manages time and priorities effectively, ensuring tasks are completed accurately and on time even in a fast-paced environment.
• Discretion & Integrity: Handles sensitive and confidential information with professionalism and sound judgement.
• Problem Solving: Approaches challenges proactively and with a solution-oriented mindset, taking initiative rather than waiting to be directed.
• Collaboration: A team player who builds strong working relationships and communicates effectively with colleagues across all levels.

Why You Will Love It Here:

• Work on real-world AI and advanced analytics solutions with measurable business impact.
• Collaborate with a global team of engineers and data scientists.
• Exposure to diverse industries, modern cloud platforms, and cutting-edge AI technologies.
• A collaborative culture that values real outcomes.
• Rapid learning opportunities and diverse challenges.
• Flat organisational hierarchy with high visibility and accessibility to our leaders.