AI Engineer

AI & ML Engineer (Agentic AI, Microsoft Stack, Enterprise Legal Systems) | Remote | United States | $140K - $200K

We are working with a well-capitalised, global law firm that is investing heavily in building
internal, enterprise-grade agentic AI systems
to transform legal workflows, knowledge management, and decision-making. This initiative is focused on developing secure, auditable, and highly reliable AI agents powered by Microsoft’s ecosystem, enabling lawyers and business teams to collaborate with AI in complex, high-stakes environments.

This is a role for an AI/ML engineer who thrives on ownership, system design, and solving ambiguous problems in regulated environments. You won’t just be building models—you’ll be designing
stateful, production-ready agent architectures
that integrate deeply with legal systems, documents, and enterprise data platforms.

What you will do:

- Design and build
agentic AI systems
using Microsoft technologies (Azure OpenAI, Azure ML, Semantic Kernel, etc.)
- Develop
stateful, multi-step agent workflows
capable of reasoning over legal documents and executing tasks across systems
- Build and optimise
RAG pipelines
to ground LLM outputs in structured and unstructured legal data
- Integrate AI agents with internal systems (document management, case systems, knowledge bases)
- Design
orchestration layers, tool usage frameworks, and execution control mechanisms
for reliable agent behaviour
- Handle real-world LLM challenges including
hallucination, context limits, latency, and cost constraints
- Implement
evaluation frameworks
(LLM-as-judge, test harnesses, monitoring pipelines) to ensure system quality
- Work closely with legal, product, and data teams to translate complex workflows into AI-driven solutions
- Design systems with
auditability, governance, and compliance
at the core
- Build scalable ML pipelines using Azure services (Azure ML, Data Factory, Synapse, etc.)
- Develop APIs and backend services in Python to support agent execution and integration
- Optimise system performance, reliability, and observability in production environments
- Rapidly prototype and iterate on internal AI tools while maintaining production standards
- Own systems end-to-end, from architecture and development through deployment and ongoing improvement
- Operate in a fast-paced environment where priorities evolve and high-impact delivery is key

What you will get:

- Ownership of
business-critical AI systems
used across legal workflows
- Opportunity to shape
foundational agent architecture
within a global enterprise
- Direct collaboration with legal experts, product leaders, and senior stakeholders
- Exposure to
cutting-edge Microsoft AI technologies
and enterprise-scale deployments
- A high-impact role in a rapidly evolving AI initiative with real autonomy
- Competitive compensation, flexible for exceptional candidates

Requirements:

Must haves:

- 5+ years of software engineering or ML engineering experience
- 2+ years building
LLM-based or agentic AI systems in production
- Strong experience with
Python and backend system design
- Hands-on experience with
Microsoft AI stack
(Azure OpenAI, Azure ML, Cognitive Services, Semantic Kernel)
- Experience building
RAG pipelines, embeddings, and retrieval systems
- Understanding of
agent orchestration, tool use, and multi-step reasoning workflows
- Experience handling
LLM limitations and failure modes
in production systems
- Strong knowledge of
data pipelines, APIs, and system integration
- Experience designing systems for
reliability, observability, and scalability
- Familiarity with
security, compliance, and governance
in enterprise environments
- Strong proficiency with Git and modern development workflows
- Ability to operate in
ambiguous, fast-moving environments
with high ownership
- Genuine capability across:
- Agent architecture and orchestration design
- LLM integration and prompt/system design
- Data grounding (RAG, semantic search, embeddings)
- Backend systems and API development
- System reliability, monitoring, and evaluation

Nice to Have:

- Experience in
legal tech or document-heavy domains
- Familiarity with Microsoft tools such as
Power Platform, SharePoint, and Microsoft Graph
- Experience with
multi-agent frameworks
and stateful execution (e.g. LangGraph, Semantic Kernel planners)
- Exposure to
LLM evaluation frameworks and benchmarking approaches
- Experience with
knowledge graphs or semantic data modelling
- Background in
regulated industries
(legal, finance, healthcare)
- Experience building
internal AI platforms or developer tooling
- Familiarity with
CI/CD and MLOps practices on Azure
- Understanding of
data privacy, auditability, and enterprise AI governance

If you are looking to take on the next challenge in your career and build
high-impact, enterprise-grade AI systems in a regulated environment
, apply now using the Easy Apply button. We are actively scheduling interviews for this role.