AI Implementation Engineer

Requirements

• You are equally comfortable writing production code, debugging an integration the night before a go-live, walking a customer's VP of Operations through an architecture decision and translating a messy business problem into a feasible agentic workflow

,• You thrive in ambiguity, make abstract problems concrete, and reduce chaos rather than amplify it when things go wrong

,• 5–8 years of relevant experience in technical implementation, post-sales engineering, solutions engineering, or hands-on software engineering with significant customer-facing exposure

,• Bachelor's degree in Computer Science or related field

,• Hands-on production experience with agentic AI, automation, LLM applications, or workflow orchestration platforms — beyond pilots

,• Strong back-end engineering skills in Python and/or Go; solid foundations in algorithms, data structures, and object-oriented programming

,• Experience designing and building APIs (REST, gRPC) and integrations across enterprise systems

,• Working knowledge of databases (PostgreSQL, Elastic, Redis, Clickhouse) and front- end frameworks (React or Angular)

,• Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes)

,• Experience deploying and operating software in multi-tenant SaaS environments

,• Understanding of security best practices and protocols for enterprise software

,• Track record of owning customer-facing delivery end-to-end — production, scale, and accountability

,• Background in fast-growing startups or enterprise platform companies

,• Strong technical judgment, calm under pressure, and excellent written and verbal communication with both engineers and business stakeholders

,• Experience working with global, distributed teams

What the job involves

• The AI Implementation Engineer owns the technical delivery and stabilization of Ema's agentic AI solutions in customer environments — from commitment through production rollout and steady state

,• This is a hands-on, post-sales, customer-facing engineering role: you build, you deliver, and you are the technical anchor the customer leans on

,• You'll work closely with Value Engineering, Product, Engineering, Infrastructure, and the customer's IT and business teams to prove that agentic AI can be implemented responsibly — not heroically

,• Own technical delivery from design alignment through production rollout and Stabilization

,• Configure, extend, and integrate Ema's agentic AI platform to meet customer requirements

,• Ensure solutions align with Ema's agentic architecture and platform capabilities

,• Write clean, efficient, maintainable code to build customer integrations, custom agents, and workflow extensions

,• Build and maintain APIs (REST, gRPC) and integrations across enterprise SaaS systems

,• Work with back-end languages such as Python and Go, and contribute to front-end interfaces (React/Angular, HTML, CSS, JavaScript) where customer-facing tooling is needed

,• Work with data stores such as PostgreSQL, Clickhouse, Elastic, and Redis to shape scalable, extensible schemas for customer deployments

,• Develop deep understanding of each customer's business processes, systems, and constraints

,• Translate business workflows into feasible agentic AI workflows — and push back when something shouldn't be built

,• Anticipate where AI implementations break: integrations, data quality, scale, edge cases

,• Be the primary technical point of contact for customer business and IT stakeholders during implementation

,• Coach customer teams and internal partners during high-stress phases — go-lives, incidents, scope changes

,• Communicate progress, risks, and decisions clearly across technical and executive audiences

,• Stand systems up in multi-tenant SaaS environments and harden them for production

,• Apply security best practices and enterprise integration patterns (auth, RBAC, audit, compliance)

,• Track success through adoption signals and outcome metrics — not just feature shipment

,• Stabilize systems post go-live under real pressure

,• Coordinate across Ema Engineering, Product, Data, Infrastructure, and Value Engineering

,• Feed customer learnings back into product and platform improvements

,• Contribute to shared standards, delivery discipline, and reusable patterns across the implementation team