Title:  Principal AI Engineer - Generative & Agentic AI, AI.DA STC

We're seeking a Senior GenAI Developer with proven experience moving AI products from prototype to production. At ST Engineering, you'll join a small, autonomous team building agentic systems that automate vision pipelines, customer interactions, and document workflows. Real problems, real users, real impact.
This is a true builder role for someone who enjoys taking ideas from notebooks to live users. You'll work closely with Software and AI Engineers to integrate workflows into production and shape how our agents interact with tools, memory, data, and humans.

What You'll Work On
• End-to-end automation of ML Vision Pipelines using AI agents
• Customer contact center agentic systems
• Document understanding and review automation
• Speech-to-text GenAI products
• Evaluating and integrating new Generative AI technologies
• Efficient serving of LLMs (hardware and software)

Key Responsibilities
• Design and improve LLM-powered agents for task planning, execution, retrieval, and memory
• Build modular agent stacks using frameworks like LangChain, CrewAI, AutoGen, or custom orchestrators
• Develop workflows that connect agents to APIs, computer vision models, and vector databases
• Productionize agents with proper observability and debuggability
• Evaluate agent behavior through logging, telemetry, and custom evaluation tools
• Work with infrastructure teams to deploy agentic systems to production, ensuring monitoring, scaling, and rollback safety

Must-Have Skills
• 5+ years in software/AI development, including 2+ years of hands-on Generative AI product experience
• Proven track record of shipping GenAI products to production using containerization and cloud platforms (Docker, Kubernetes, GCP/AWS)
• Strong Python skills with experience building reusable AI Agent stacks & RAG pipelines
• Hands-on experience with LLM APIs (OpenAI, Anthropic, HuggingFace, etc.) and building prompt/tool workflows
• Experience integrating vector databases (Weaviate, FAISS, pgvector, Pinecone)
• Experience with multi-agent orchestration (CrewAI, AutoGen, LangGraph, or custom)
• Understanding of agent design principles (memory management, context management, tool contracts)

Bonus Skills
• Exposure to hybrid workflows combining LLMs with computer vision
• Knowledge of event-driven or streaming agents (Kafka, LCEL, reactive frameworks)
• Experience building interfaces with Streamlit, Gradio, or browser automation
• Knowledge of Model Context Protocol (MCP) Agent to Agent (A2A) or similar standards

What We Offer
• Small, agile team (5–6 engineers + interns) with autonomy and real ownership
• Startup feel with big company resources:
– International environment where the majority of the team and leadership is from startups or big international corporations (Lazada, Gojek, IBM) and from various countries
– Low-bureaucracy, high-impact environment where your code directly supports next-gen AI deployment
– Experimentation and self-development are in our culture
– Knowledge sharing and collaboration
• Direct collaboration with top AI researchers and computer vision scientists
• Hybrid work setup: ~2–3 days in office per week