Senior AI Engineer

Coaction Global•Morristown, NJ

39d•$140,000 - $190,000

About The Position

At Coaction, we’re a unique mix of leaders, achievers, thinkers, and team players with a high-performance mindset and a diverse skillset. We bring our industry expertise together to continually push the boundaries of what insurance can be for our clients. At Coaction, innovation is key to our continued success and growth. As we expand our digital and data capabilities, Artificial Intelligence will play a critical role in enhancing underwriting, operations, and customer experience. We believe the best solutions happen when product, engineering, data, security, and the business partner as one integrated team—open to ideas, ready to challenge the status quo, and focused on delivering measurable outcomes in a regulated industry. This is our first dedicated AI Engineering role. This role will be instrumental in shaping how we design, build, deploy, and operate AI-powered solutions safely and responsibly. The ideal candidate is pragmatic and hands-on—focused on putting AI into production (not research-only)—and comfortable building repeatable patterns, playbooks, and guardrails from the ground up.

Requirements

5+ years of software engineering experience building production systems (APIs, services, data pipelines, or enterprise integrations).
Bachelor’s or Master’s Degree in Computer Science, Information Systems, or related field, or equivalent work experience.
Strong proficiency in at least one production language such as Python, C#, Java, or similar.
Experience integrating third-party APIs and services; strong understanding of distributed systems, REST/JSON, and authentication/authorization patterns.
Hands-on experience implementing LLM-based solutions (prompting, structured outputs, tool/function calling) and/or ML-enabled services.
Working knowledge of RAG concepts (embeddings, vector search, grounding/citations); experience with vector databases or enterprise search platforms is a plus.
Awareness of LLMOps/MLOps practices: versioning, evaluation, monitoring, incident response, and change control.
Experience with cloud platforms (AWS and/or Azure) and production operations (secrets management, logging/monitoring, cost controls).
Strong engineering hygiene: source control, code review, automated testing, CI/CD, and performance monitoring.
Understanding of AI risk and security considerations (prompt injection, data privacy/PII handling, vendor/model risk management) in regulated environments.
Effective verbal and written communication skills; ability to translate business needs into technical solutions.

Nice To Haves

experience with vector databases or enterprise search platforms is a plus.

Responsibilities

Implement AI-enabled features, services, and APIs that integrate into existing enterprise workflows and applications, while adhering to established engineering, architecture, and security practices.
Design and build integration patterns for external AI services (LLMs and ML APIs), including secure data handling, access controls, and auditability.
Develop and maintain retrieval-augmented generation (RAG) solutions for document-heavy workflows (e.g., submissions, endorsements, claims documentation) using enterprise data sources.
Collaborate with Architecture and Engineering to support the implementation of an Agentic AI platform reference architecture and implementation
Create reusable AI components including Agentic Platform components to accelerate delivery across multiple use cases.
Partner with architecture, engineering, data, and business stakeholders to translate needs into solution designs, requirements, and delivery plans.
Establish AI engineering best practices for testing and evaluation (quality, safety, regression testing), and incorporate them into CI/CD pipelines.
Implement monitoring and observability for AI solutions (latency, cost, quality signals, guardrail events) and define operational runbooks.
Collaborate with others to support AI governance controls (vendor/model intake, risk reviews, documentation, and change management).
Contribute to security hardening for AI systems, including safeguards against prompt injection, data leakage, and misuse.
Document designs and deliver knowledge transfer to broaden internal capability and reduce reliance on external partners over time.
Stay up to date with AI engineering tools, platforms, and patterns and recommend pragmatic adoption aligned to business value and risk posture.