Job Description
Design and develop the core architecture of the AI platform used to build and deploy AI agents and AI-powered services. Architect and implement agent orchestration frameworks using Lang Chain and Lang Graph for complex multi-step AI workflows. Develop and maintain platform SDKs, Python libraries, and developer tooling to standardize integration with models, tools, and enterprise systems. Build and maintain the LLM integration layer, supporting multiple model providers and internal model deployments.
Design platform components for prompt lifecycle management, tool calling frameworks, agent execution engines, and memory management. Implement observability, tracing, and evaluation capabilities using tools such as Langfuse to monitor prompts, agent reasoning, and system performance. Ensure the platform meets requirements for scalability, reliability, security, and performance in production environments. Collaborate with Applied AI Engineers to define best practices, reusable patterns, and platform standards for AI development.
Lead technical design decisions and contribute to platform architecture and roadmap. Mentor junior engineers and contribute to engineering excellence across the AI platform team.
Qualifications:
- 5-6 years of experience in backend, platform, or distributed systems engineering.
- Strong programming expertise in Python and experience building platform frameworks or SDKs.
- Hands‑on experience building LLM‑powered platforms, AI infrastructure, or agent‑based systems.
- Strong experience with Lang Chain, Lang Graph, or similar AI orchestration frameworks.
- Deep understanding of RAG architectures, prompt engineering, tool integration, and agent workflows.
- Experience building microservices architectures and scalable distributed systems.
- Strong understanding of observability, logging, tracing, and performance monitoring for AI systems.
- Experience building internal AI platforms or AI developer tooling.
- Experience with vector databases, semantic search, and retrieval pipelines.
- Familiarity with AI observability and evaluation tools such as Langfuse.
- Experience integrating with multiple LLM providers or self-hosted models.
- Experience working with containerized environments and cloud-native architectures.
Competencies:
- Strong system design and architectural thinking.
- Ability to build reusable platform capabilities for engineering teams.
- Technical leadership and mentorship.
- Strong collaboration and communication skills.
- As per client policy
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).