The AI Enablement team gives every team at Extend the AI tooling it needs to do its best work. We pair directly with business users in finance, support, claims, sales, recruiting, and operations to understand how they work, then build the agents, connectors, and skills that change it. This is an engineering role first.
Compensation
Expected Pay Range: $155,000 - $170,000 per year salaried*
Responsibilities
Pair with business users to run workflow analysis and process mapping, find the highest-leverage problems, and turn ambiguous requests into scoped technical plans.
Design and ship secure MCP connectors to Extend's internal systems and third-party SaaS: finance, CRM, data warehouse, expense management, product analytics, support, ATS, and the long tail beyond.
Build agent-to-agent integrations using A2A and similar protocols, so specialized agents can delegate to each other safely across domains.
Choose and configure the right agent harness or orchestrator for each job, and build multi-agent patterns (planner/executor, specialized sub-agents) where they genuinely help.
Stand up Extend's evaluation practice for agents and skills: golden datasets, regression suites, LLM-as-judge, tracing, and drift detection.
As an AI Engineering Team/Project Lead on our Data & AI team, you will work on a project team with two other engineers, leading the work of turning real engineering and operations workflows into agents that people across Halliburton rely on every day. You will build on our established agent platform, which spans Databricks and Azure, and extend it as you go.
Compensation
Compensation is competitive and commensurate with experience.
Responsibilities
Lead from the keyboard- Work on a project team with two other engineers, write production code every day, and take on the hardest technical problems yourself.
Ship workflows that get used- Lead your team in turning real engineering and operations workflows into production agents on our platform, from first conversation to daily use.
Own requirements and roadmap- Work with business stakeholders and the people who do the work to define requirements, cut scope and keep a roadmap focused on what delivers the most value.
Set and review architecture- Define the architecture for your team's agents, review designs and code, and hold a high bar for reliability, security and maintainability.
Connect agents to the business- Use secure tool and data connectors (including MCP servers) to give agents governed access to Halliburton data and engineering applications.
Requirements
Degree in Computer Science, Data Science or a related technical field
Nice to have: Databricks
Nice to have: Mosaic AI Agent Framework / Agent Bricks
We are looking for a Senior AI Engineer with deep expertise in Agentic AI, Multi-Agent Systems, MCP (Model Context Protocol), and LLM-powered applications. This role requires an engineer who can independently drive AI initiatives from idea to production.
Responsibilities
Design, build, and deploy Agentic AI solutions using modern LLMs and AI frameworks
Architect and implement multi-agent systems with agent orchestration, planning, memory, and tool usage capabilities
Design and develop MCP-based integrations to connect agents with enterprise systems, APIs, data sources, and external tools
Build Retrieval-Augmented Generation (RAG) systems using enterprise knowledge sources and vector databases
Define agent workflows, reasoning strategies, evaluation frameworks, and guardrails for reliable AI behavior
Requirements
Bachelor's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field
Master's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field
Design, build, and secure the Model Context Protocol (MCP) infrastructure that connects large language models to the tools, data, and systems they need to act autonomously.
Compensation
Minimum Compensation: USD 120,000
Maximum Compensation: USD 420,000
Responsibilities
Build production MCP servers and clients from scratch that correctly implement the specification
Implement and operate both standard transports — stdio for local servers and Streamable HTTP for remote ones
Wire MCP servers into real hosts: Claude (Claude Desktop extensions and remote custom connectors), ChatGPT (connectors and the Apps SDK, including tool-rendered widgets), Cursor, and other MCP clients
Expose databases, SaaS APIs, and internal services as well-designed MCP tools and resources
Defend the tool layer against the attacks unique to this ecosystem — tool poisoning, rug pulls, prompt injection via tool results, and data exfiltration through legitimate channels
You are the senior technical authority for how Sparta builds agents. You design and build the harness that runs Leonidas AI's agents, set the patterns the rest of the team and the wider engineering group follow, and stay in the code on the hardest problems.
Responsibilities
Set the technical direction and author the target architecture for the agent platform
Hands on AI development including context engineering across branched conversations and handoffs between specialist agents
Define how agents are evaluated using golden question sets, offline and online evals in CI, tracing and feedback loops
Design the agent-to-agent API, MCP server and headless modes
Own reliability, cost and safety including latency, token budgets, failure handling, guardrails, and security model for agents
Lead the design, build, and operation of agents and agentic workflows in production, owning agents end to end from a loosely defined business problem to a reliable, measured, and trusted system.
Locations (3)
Minneapolis, Minnesota, United States
Chicago, Illinois, United States
New York, New York, United States
Compensation
For our Sr. Manager positions, including the position of Lead AI Engineer, our compensation range is from $125,000 to $175,000 on an annualized basis, which is inclusive of an annual bonus opportunity of up to 25% of base salary
Responsibilities
Lead agent design and delivery
Own agents end to end: scope the problem with operators and the product owner, set the technical design, break the work into milestones, and lead the build through launch and beyond
Make the core architecture calls for each agent: level of autonomy, agent loop design, single agent versus multi agent orchestration, stopping conditions, escalation paths, and where deterministic code must own a step
Strong understanding of agent loops (ReAct, plan-and-execute) and how models decide between calling a tool and answering directly, with hands‑on exposure to frameworks such as LangGraph, LangChain, OpenAI Agents SDK, Claude Agent SDK, or PydanticAI
Working knowledge of multi‑agent patterns (orchestrator/worker, router, supervisor) and handoffs, using LangGraph, CrewAI, or AutoGen
Experience defining function‑calling specs and typed tool contracts using JSON Schema, Pydantic, and OpenAPI to turn user intents into deterministic actions
Requirements
Bachelor's degree in Business, Finance, Computer Science, or related field
Business Analyst focused on agentic AI/LLM solutions, requiring expertise in agent loops, multi-agent patterns, function-calling specs, and RAG design.
Responsibilities
Gathering and documenting requirements directly with business users, product, and engineering
Writing user stories, acceptance criteria, process flows, and functional and API specifications
Translating business goals into measurable success metrics and explaining technical trade-offs to non-technical stakeholders
Requirements
Bachelor’s degree in Business, Finance, Computer Science, or related field
Nice to have: Buy-side trading workflows (order lifecycle, order staging, routing, execution, allocations, post-trade)
Nice to have: Portfolio management workflows (portfolio construction, rebalancing, model portfolios, cash management, what-if analysis)
Nice to have: Pre-trade and post-trade compliance, restricted lists, and best execution requirements
Nice to have: OMS/EMS platforms (Charles River, Aladdin)
Design agents and their tools so they extend to new platforms and use cases without a rebuild
Lead design reviews and code reviews for agent work, holding a high bar for tool design, context engineering, state management, and failure handling
Requirements
7+ years of software engineering experience, with backend or platform work as a core part of it, with 2+ years building LLM based systems in production