Senior Staff Machine Learning Engineer, AI Agent Platform

GEICO
New York, NY, United States
2 months ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
2 years minimum
Compensation
$130,000.0 - $300,000.0
Working hours
Regular working hours
Job source

Tech stack

Java (Programming Language) Artificial Intelligence Amazon Web Services Microsoft Azure C Sharp (Programming Language) C++ (Programming Language) Cloud Computing Continuous Integration Elasticsearch Information Management Interoperability Python (Programming Language)
+23 more
PostgreSQL Machine Learning MongoDB Neo4j Open Source Technology Role-Based Access Control Redis Azure Machine Learning Software Safety Software Engineering Test Execution Engine Management of Software Versions Workflow Management Systems Large Language Models Multi-Agent Systems Apache Spark Kubernetes Apache Kafka Hardware Infrastructure Virtual Agents Marketplace GPT Golang

Job description

GEICO is seeking an exceptional Sr. Staff ML Engineer to join our AI organization. You will serve as a technical leader and key architect for GEICO’s virtual assistant platform that elevates productivity for 30K+ internal associates and the customer experience for millions of policyholders., * Technical Vision & Architecture: Define the long-term technical strategy for GEICO’s AI agent platform - including multi-agent orchestration, AI agent lifecycle management, evaluation frameworks, skill registries and marketplace, and workflow orchestration.

  • AI Agent Skills & Marketplace: Architect an enterprise skill ecosystem - reusable capability packages that encode domain expertise and workflows into portable, discoverable modules. Build and govern an internal skill marketplace with versioning, security vetting, approval workflows, progressive disclosure loading, and usage analytics.
  • Harness & Context Engineering: Lead design of production-grade AI agent harnesses (tool dispatch, context management, error recovery, session state, fine-grained Authn/AuthZ) that makes AI agents reliable for long-running workflows. Apply feedforward guides (linters, architecture constraints, spec-driven validation) and feedback sensors (test execution, LLM-as-judge) mixing computational and inferential controls. Design context engineering systems that treat the LLM context window as a managed resource - memory hierarchies, RAG pipelines, context compaction, scratchpads, and dynamic skill/tool loading.
  • Platform & Interoperability: Own high-performance platform components powering end-to-end agentic workflows: MCP server/registry management, A2A communication infrastructure, prompt management, workflow orchestration, guardrail enforcement, and observability pipelines.
  • AI Safety & Governance: Establish AI agent governance frameworks including bounded autonomy, human-in-the-loop escalation, audit trails, prompt guardrails, and RBAC/ABAC access controls. Extend governance to skill-level security - vetting published skills for hidden payloads, injection vectors, and data exfiltration risks.
  • Leadership: Collaborate cross-functionally with data scientists, engineers, product managers, and designers. Mentor engineers at all levels. Elevate AI engineering best practices - including harness engineering patterns and agentic coding tools - across the company., Great Rewards: We offer compensation and benefits built to enhance your physical well-being, mental and emotional health and financial future.
  • Comprehensive Total Rewards program that offers personalized coverage tailor-made for you and your family’s overall well-being.
  • Financial benefits including market-competitive compensation; a 401K savings plan vested from day one that offers a 6% match; performance and recognition-based incentives; and tuition assistance.
  • Access to additional benefits like mental healthcare as well as fertility and adoption assistance.
  • Supports flexibility- We provide workplace flexibility as well as our GEICO Flex program, which offers the ability to work from anywhere in the US for up to four weeks per year.

Requirements

Do you have experience in Test Execution (Quality assurance practices)?, * 8+ years of professional software development experience with at least two languages (Java, C++, Python, Go, or C#).

  • 6+ years designing and building AI/ML platforms using open-source/cloud-agnostic components (Elasticsearch, Qdrant, Kafka, PostgreSQL, MongoDB, Spark, Ray, Temporal, Redis, Neo4j, etc.).
  • 5+ years managing end-to-end SDLCs (CI/CD, Kubernetes, testing, monitoring, production support).
  • 4+ years building training, fine-tuning, and inferencing systems for LLMs, especially on GPU infrastructure.
  • 3+ years designing and operating multi-agent or agentic AI systems in production.
  • Strong understanding of context engineering - memory architectures, RAG, context compaction, and dynamic information management for LLMs.
  • Demonstrated track record leading technical initiatives, setting architectural direction, and mentoring across teams.
  • Bachelor’s degree in CS, Engineering, or related field; advanced degree highly desirable.

Preferred Qualifications

  • 6+ years with cloud providers (Azure, AWS), including container orchestration and GPU compute.
  • 3+ years building agentic workflows with open-source and proprietary LLMs (Llama, Qwen, Claude, Gpt, etc.).
  • Hands-on experience with MCP and A2A protocols - MCP server development, AI agent card discovery, task delegation patterns.
  • Experience with harness engineering. (tool dispatch, error recovery, session state, sub-agent coordination, planning & reasoning)
  • Experience designing AI agent skill systems: building and governing reusable skill packages, skill marketplaces with discovery, versioning, security vetting, and progressive disclosure.
  • Experience with context engineering at scale: memory hierarchies, RAG optimization, compaction/summarization, state isolation, etc.
  • Experience with multi-agent orchestration frameworks (LangGraph, AutoGen, CrewAI).
  • Experience with LLM observability & evaluation platforms (LangSmith, Arize Phoenix, Langfuse).
  • Experience building guardrail systems (prompt injection defense, PII detection, skill-level security auditing).
  • Understanding of AI safety, model governance, and regulatory compliance in regulated industries.

If you are passionate about pushing the boundaries of generative AI platforms, thrive in a hands-on technical leadership role, and enjoy solving complex, large-scale problems, we encourage you to apply!

Benefits & conditions

3.13.1 out of 5 stars New York, NY 10001 $130,000 - $300,000 a year - Full-time, Pulled from the full job description

  • Tuition reimbursement
  • Health insurance
  • Adoption assistance
  • 401(k) 6% Match

About the company

Great Company: At GEICO, we help our customers through life’s twists and turns. Our mission is to protect people when they need it most and we’re constantly evolving to stay ahead of their needs.

We’re an iconic brand that thrives on innovation, exceeding our customers’ expectations and enabling our collective success. From day one, you’ll take on exciting challenges that help you grow and collaborate with dynamic teams who want to make a positive impact on people’s lives.

Great Careers: We offer a career where you can learn, grow, and thrive through personalized development programs, created with your career - and your potential - in mind. You’ll have access to industry leading training, certification assistance, career mentorship and coaching with supportive leaders at all levels.

Great Culture: We foster an inclusive culture of shared success, rooted in integrity, a bias for action and a winning mindset. Grounded by our core values, we have an an established culture of caring, inclusion, and belonging, that values different perspectives. Our teams are led by dynamic, multi-faceted teams led by supportive leaders, driven by performance excellence and unified under a shared purpose.

As part of our culture, we also offer employee engagement and recognition programs that reward the positive impact our work makes on the lives of our customers.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

40 sec

Generative pre-trained transformer models powering code completions

lgonta lgonta +1 · WWC 2024

3:55 min

Demonstrating semantic routing thresholds with the Redis vector library

2:24 min

Comparing Neo4j and GraphQL conceptual models

William Lyon · LIVE

3:22 min

Evaluating advanced artificial intelligence platforms for daily recruitment

Rudi Bauer Rudi Bauer +1 · Cappuccino with HR

51 sec

Assessing GPT-4o performance for pull request feedback

Merrill Lutsky Merrill Lutsky · WWC 2025

3:45 min

Fusing developer experience and platform engineering for agentic SDLC

Julia Kordick Julia Kordick · WWC Europe 2026

Videos

See all

Related articles

See all