Senior AI Engineer at TechX Corporation

, , Vietnam -

Full Time

Start Date

Immediate

Expiry Date

28 Sep, 26

Salary

0.0

Posted On

30 Jun, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

GenAI, Agentic Frameworks, LangChain, LlamaIndex, RAG, REST API, gRPC, WebSocket, Microservices, Model Context Protocol, Vector Databases, Prompt Engineering, Python, Async Design, Event-Driven Design, LLM Integration

Industry

IT Services and IT Consulting

Description

Company Overview: At TechX, we are pioneers in delivering cutting-edge solutions that empower businesses to thrive in today’s digital landscape. With a strong focus on Cloud Transformation (AWS), Data Modernization, and Generative AI, we bring unparalleled expertise to drive innovation, efficiency, and growth for our clients. We specialize in banking and financial services, retail, manufacturing, and transportation, delivering impactful solutions that address industry-specific challenges and significant market shifts. Together, we’ll build a future where innovation knows no limits. This role sits on our Agentic AI team — building our AI platform for enterprise and regulated industries, with strong governance, security, and human oversight. Job Overview: We are looking for a Senior AI Engineer to build the runtime that powers our agentic AI platform. You will develop the agent orchestration layer — task routing, tool use, human-in-the-loop escalation, and audit hooks — that allows our agents to execute real workflows reliably and verifiably. This is the core engineering role that turns the reference architecture into a working platform. Key Responsibilities: Build and own the agent runtime and orchestration layer: task routing, multi-agent coordination, and tool-use execution. Implement human-in-the-loop (HITL) flows, approval gates, escalation logic, and end-to-end audit / trace hooks. Develop the control plane and APIs that let domain teams plug in new agents and workflows. Deliver a runtime MVP capable of executing demo workflows end-to-end with a complete audit trail. Integrate with LLM APIs and self-hosted models, vector databases, and the RAG / knowledge layer. Collaborate with the AI/ML Architect, RAG, and platform engineers to ensure performance, reliability, and security. Key Requirements: Minimum 3+ years of software / AI engineering, with hands-on experience building GenAI or agentic applications. Strong experience with agentic frameworks and orchestration (LangChain, LlamaIndex) and a solid grasp of RAG, agentic, and DeepSearch patterns. Strong backend engineering skills: REST API, gRPC, WebSocket, microservices, async / event-driven design. Solid understanding of the Model Context Protocol (MCP) and agent tool-use / function-calling patterns. Experience integrating with vector databases (Qdrant, ChromaDB, OpenSearch, Pinecone) and LLM APIs. Familiarity with AI platforms (Azure AI, Vertex AI; bonus AWS Bedrock / SageMaker) and self-hosted inference (vLLM, llama.cpp, GGUF models). Experience implementing logging, observability, audit trails, or HITL workflows is a strong plus. Strong computer science foundation and proficiency in prompt engineering. What We Offer: Innovative Environment: A dynamic and collaborative work environment where innovation is encouraged. Professional Growth: Opportunities for professional growth and development through continuous learning and exposure to cutting-edge technologies. Competitive Package: Competitive salary and benefits package Impactful Work: The chance to work on cutting-edge projects with industry-leading clients, making a tangible impact on their business success. Apply now! Due to the high volume of applicants, only shortlisted candidates will be contacted. We apologize for this inconvenience!

Responsibilities

Build and own the agent runtime and orchestration layer, including task routing and multi-agent coordination. Implement human-in-the-loop flows, audit hooks, and APIs for integrating new agents and workflows.