In this role, you will drive key technical decisions and take ownership of critical systems that leverage advanced agentic frameworks and large language models (LLMs) to enable intelligent, multi-step reasoning workflows.

Role & responsibilities :

- Architect Core Agentic Systems : Lead the design of modular, high-throughput components for a large-scale AI platform, transitioning from simple API wrappers to stateful, autonomous systems.

- Scale Cloud-Native Infrastructure : Build and optimize high-concurrency backend services and REST/gRPC APIs within a distributed, containerized environment (e.g., Kubernetes, Docker) to support sub-second model orchestration.

- Engineer Advanced Reasoning : Design and implement sophisticated agent workflows, specifically focusing on multi-agent collaboration, dynamic tool orchestration, and ReAct/Chain-of-Thought reasoning loops.

- Productionize ML & RAG : Integrate LLMs into production via high-performance pipelines, utilizing Vector Databases (like Pinecone, Milvus, or Weaviate) and advanced RAG techniques such as hybrid search and query expansion.

- Establish LLM Excellence : Define organizational best practices for prompt engineering, model fine-tuning, and performance benchmarking, ensuring a balance between cost-efficiency and output quality.

- Optimize System Reliability : Partner with DevOps and Infrastructure teams to manage cloud architecture, focusing on LLM observability, automated scaling, and 99.9% system uptime.

- Develop AI Monitoring & Debugging : Implement advanced tracing and logging strategies for non-deterministic systems, using tools like LangSmith or Arize Phoenix to debug reasoning failures and "hallucination" triggers.

- Secure Agentic Operations : Ensure robust system behavior by implementing security guardrails, PII masking, and RBAC (Role-Based Access Control) to prevent prompt injection and data leakage.

- Lead & Mentor : Serve as a technical bridge between product stakeholders and the engineering team, providing deep-dive code reviews and mentoring junior engineers in the rapidly shifting AI landscape.

Preferred candidate profile :

- Python Expertise : 8+ years of software engineering experience with strong proficiency in Python, including async programming, testing, and packaging

- LLM / Agentic Systems Development : Experience building LLM-powered applications using frameworks such as LangChain, LangGraph, or equivalent abstractions

- RAG & Retrieval Systems : Experience with retrieval-augmented generation, vector databases (e.g., PGVector), and embedding pipelines

- LLM Integration : Hands-on experience integrating and operating systems using Azure OpenAI or OpenAI APIs

- Backend & API Design : Experience designing scalable REST APIs and microservices architectures

- Cloud & Infrastructure (AWS) : Strong experience designing and deploying systems using AWS services (Lambda, API Gateway, S3, ECR, Secrets Manager)

- Data & Persistence : Experience with PostgreSQL

- Containerization : Proficiency with Docker and container-based deployment workflows

Nice to Have Skills :

- Applied ML : Experience with applied ML beyond LLMs (e.g., forecasting, classification, etc.)

- Agent Protocols : Experience with Model Context Protocol (MCP) or similar agent communication standards

- Security & Code Quality : Familiarity with tools such as SonarQube, Snyk, or similar security and code analysis platforms