Senior AI Engineer

Job Description

Our client, a global consultancy specializing in SaaS solutions, is seeking a
Senior AI Engineer
to take ownership of the architecture and development of the orchestration layer powering their next-generation Co-Pilot system. This role will shape the core intelligence behind a sophisticated multi-agent platform, translating an ambitious technical vision into a scalable, production-ready AI environment.

Role Overview

The Senior AI Engineer will design the system responsible for coordinating multiple AI agents, managing their workflows, and integrating human oversight where necessary. This position requires a strong technical leader capable of building reliable infrastructure, defining communication patterns, and ensuring the orchestration layer is robust, flexible, and ready for large-scale deployment.

Primary Responsibilities

Architecture & System Design (40%)

• Develop the central orchestration engine using LangChain/LangGraph and the Model Context Protocol (MCP).
• Create a persistent workflow layer that handles document pipelines, agent states, and human-in-the-loop processes.
• Define structured communication standards, including JSON schemas and lifecycle management for agents.
• Build an internal registry for agent versioning, discovery, and dynamic routing.
• Engineer resilient workflows capable of automatic retries, failover handling, and partial output preservation.
• Establish a routing system that selects the optimal model (GPT, Claude, Gemini, or open source) based on performance, cost, and accuracy.

Implementation & Development (30%)

• Build the execution engine coordinating reasoning cycles, validations, and retrieval tasks.
• Develop foundational system-level agents such as reasoning, retrieval, memory, parsing, and validation agents.
• Implement asynchronous processing using technologies like RabbitMQ, Kafka, or SQS to support long-running jobs.
• Design prompt versioning tools, testing frameworks, and A/B evaluation workflows.
• Create observability pipelines using OpenTelemetry, LangSmith, and custom telemetry for detailed tracing.

Collaboration & Cross-Functional Integration (20%)

• Partner with the Knowledge Graph team to merge vector embeddings with graph-based reasoning.
• Work with data scientists to integrate prompts, reasoning chains, and experimentation workflows.
• Coordinate with UI engineers on WebSocket and REST interfaces for real-time agent interactions.
• Connect orchestration services with backend utilities such as ETL systems and session management tools.

Leadership & Direction (10%)

• Guide architectural reviews and ensure technical standards across the AI platform.
• Evaluate emerging technologies and recommend new frameworks, tooling, and models.
• Establish best practices for testing, documentation, and coding guidelines.
• Contribute to development planning and mentor junior AI engineers.

Candidate Profile

Experience

• 8+ years in software engineering, AI/ML development, or related fields.
• At least 3 years working directly with large language models, agent frameworks, or multi-agent systems.
• Experience shipping production-grade AI solutions in complex environments.
• Prior leadership or technical ownership in engineering initiatives.

Technical Skills

• Advanced Python expertise, particularly with asynchronous programming and static typing.
• Strong familiarity with agent orchestration frameworks such as LangGraph or LangChain.
• Hands-on experience with major LLM providers (OpenAI, Anthropic, Google) and prompt optimization techniques.
• Proficiency with FastAPI or comparable asynchronous web frameworks.
• Deep knowledge of vector databases such as Pinecone, Weaviate, FAISS, or Chroma.
• Working understanding of graph technologies (Neo4j, TigerGraph) and query languages like Cypher or SPARQL.

Please note:
This job posting is just a preview of the full scope of the position. A comprehensive job description is shared by a member of our team