This role sits in the company's Transformation Command Center and places you inside the front-line teams of its core business units.
You will take on high-stakes operational problems that are unclear and complex, with full technical ownership of the work.
You will design, build and launch production systems, including agent-based systems, enterprise retrieval-augmented generation (RAG) engines, full-stack microservices and decision tools.
You act as the technical lead, pairing solid engineering with a product outlook to turn messy operations into workable production designs.
Beyond single-use solutions, you will create reusable SDKs, shared libraries and architecture guides that other teams can adopt across the company.
Responsibilities
Set out the full architecture for embedded AI projects, covering multi-agent coordination, state machines, latency and cost limits, security boundaries and back-end integration.
Build stateful agent workflows that follow the company's agent governance rules, using LangGraph, Temporal or event-driven state machines, with strict controls for tool calls, sandboxed execution and deterministic fallbacks.
Design production RAG systems using hybrid search, re-ranking, metadata filtering and semantic caching, shaping the company's context architecture as it grows.
Deploy agent services and scheduled workflows to runtimes such as Domino Data Lab, Apache Airflow, Kubernetes microservices and serverless compute on AWS, GCP or Azure.
Create offline and online evaluation frameworks, such as LLM-as-a-judge, synthetic test sets, human review queues and live A/B tests, to track model drift, hallucination rates and task completion.
Turn custom deployments into reusable internal SDKs, API building blocks and UI components, mentor engineers, and write technical documentation for patent disclosures.
Work alongside business unit leaders to map complex processes, cut through noise and pinpoint where applied AI will deliver measurable gains.
Act as the technical authority with business unit vice presidents and managing directors, explaining model behavior, failure modes and performance trade-offs in plain terms.
Requirements
Bachelor's degree in computer science, software engineering or a related technical field, or four or more years of work experience.
Six or more years of relevant experience, which can come from work, military service, specialized training or a combination of these.
Extensive hands-on work with frontier LLMs (Anthropic Claude, OpenAI, Google Gemini) and agentic developer tools (Claude Code, Cursor, Copilot) to deliver scalable solutions and hit business goals.
Four or more years shipping production software, or proven experience putting LLM applications, agent workflows or autonomous tool-calling pipelines into production.
Strong Python and modern TypeScript/Node.js skills for full-stack API integration and back-end orchestration.
Proven record building offline evaluation benchmarks and online evaluation and observability pipelines covering latency, token cost, hallucination tracking and eval-driven development.
Advanced full-stack experience across Python, SQL and modern JavaScript/TypeScript.
Proven record designing offline and online eval harnesses, guardrail frameworks and observability systems covering latency, token optimization and tracing.
Ability to scope unclear technical work on your own and present architecture to senior executives.
Ability to work directly with enterprise stakeholders, turn vague business needs into technical architecture and lead delivery from start to finish.
Even better:
Master's degree in computer science, machine learning, robotics or a related technical field.
Experience building and scaling central context platforms or enterprise search engines similar to the company's internal enterprise context layer platforms.
Prior forward-deployed engineering, solutions architecture or technical consulting work at top technology firms or hyperscalers.
History of turning one-off operational builds into shared enterprise libraries, with technical publications or filed patents.
Domain knowledge in telecommunications, network capacity optimization, capital planning or large-scale customer care operations.
Deep retrieval and context architecture expertise: production RAG pipelines, vector databases (pgvector, Milvus, Pinecone), hybrid dense and sparse/lexical search and dynamic context management.
Proven deployment of containerized services and data workflows on Domino Data Lab, Apache Airflow, Kubernetes (EKS/GKE) and AWS, GCP or Azure.
Experience with Docker, API design and cloud environments (AWS, GCP or Azure).
You are encouraged to apply even if you do not meet every item in the even better list.
Conditions
Hybrid role with a defined work location that includes working from home and a minimum of 3 days per week in the office, set by your manager.
You are responsible for following the hybrid work policies.
Scheduled at 40 hours per week.
Benefits
Medical, dental and vision coverage, short- and long-term disability, basic and supplemental life insurance, AD&D insurance, identity theft protection, pet insurance, and group home and auto insurance.
Matched 401(k) savings plan.
Up to 8 company-paid holidays and up to 6 personal days per year.
Paid parental leave, adoption assistance and tuition assistance, plus other incentives.
Newly hired employees receive up to 15 days of vacation per year, increasing with additional service.
Depending on the role, possible premium pay such as overtime, shift differential, holiday pay and allowances.
Part-time coverage varies with individual circumstances.
Pay varies by location and confirmed job-related skills and experience. This is an incentive-based role with potential to earn more. Part-time pay is adjusted to hours.
Full-time salary range for the listed location(s): $120,500.00 - $231,000.00.