Software Engineer, Agentic AI Platform

This engineering role focuses on scaling and optimizing a production Generative AI / conversational platform for enterprise customers. You will:

• Scale and optimize the conversation engine to support high concurrency across chat channels (e.g., Microsoft Teams, Slack, Web) while minimizing memory footprint and latency.
• Design and implement clean, modular, and scalable API abstractions for the conversation platform and related services.
• Build developer- and operator-facing infrastructure (APIs, dashboards, tooling) that enables configuration, monitoring, and iterative improvement of generative models for domain-specific enterprise use cases.
• Implement robust logging, tracing, and observability to provide actionable performance insights, enable fast triage, and drive reliability improvements.
• Collaborate closely with ML engineers, application engineers, product managers, and customer support to ship features, tune performance, and operationalize model-driven workflows.
• Optimize runtime pipelines to incorporate private domain knowledge per customer, enable real-time multilingual translation where required, and maintain secure handling of customer data.
• Advocate and champion best practices for API design, code quality, testing, scalability, and performance across the engineering team.

To be successful in this role you have:

• A bachelor’s degree (or higher) in computer science or a related field, or equivalent practical experience.
• 2 years of professional software engineering experience building systems at scale.
• Strong foundation in computer science fundamentals (data structures, algorithms, concurrency, networking).
• Demonstrated experience designing and building scalable APIs and distributed systems.
• Proven ability to diagnose and resolve performance issues using tracing, logging, and metrics (experience with observability tooling such as OpenTelemetry, Prometheus, etc. is a plus).
• Proficiency in at least one backend programming language commonly used for scalable systems (for example: Python, Java, Go, or similar).
• Experience working cross-functionally with ML engineers, product teams, and SRE/ops teams.
• Excellent communication skills and the ability to clearly explain technical trade-offs and design decisions.

• Hands-on experience with Generative AI / LLM-based products or conversational agents.
• Familiarity with cloud platforms (AWS, GCP, Azure) and container/orchestration tooling (Docker, Kubernetes).
• Experience building developer tooling, configuration UIs, or automation that enables non-expert configurators to tune model-driven behavior.
• Background in real-time systems, multilingual translation systems, or integrating private domain knowledge into inference pipelines.

CareerTakes and our client are Equal Opportunity Employers committed to building a diverse and inclusive workforce. We prohibit discrimination or harassment of any kind. To support a fair and efficient hiring process, AI tools may be used to assist with application review or resume screening. These tools do not replace human decision-making. Final hiring decisions are made by people.

If you have questions about how your data is used, please contact us directly.